State representation learning for control: An overview
Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent....
Saved in:
| Published in | Neural networks Vol. 108; pp. 379 - 392 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
United States
Elsevier Ltd
01.12.2018
Elsevier |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0893-6080 1879-2782 1879-2782 |
| DOI | 10.1016/j.neunet.2018.07.006 |
Cover
| Abstract | Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent’s actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning.
This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research. |
|---|---|
| AbstractList | Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent's actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research. Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent’s actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research. Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent's actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research.Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular kind of representation learning where learned features are in low dimension, evolve through time, and are influenced by actions of an agent. The representation is learned to capture the variation in the environment generated by the agent's actions; this kind of representation is particularly suitable for robotics and control scenarios. In particular, the low dimension characteristic of the representation helps to overcome the curse of dimensionality, provides easier interpretation and utilization by humans and can help improve performance and speed in policy learning algorithms such as reinforcement learning. This survey aims at covering the state-of-the-art on state representation learning in the most recent years. It reviews different SRL methods that involve interaction with the environment, their implementations and their applications in robotics control tasks (simulated or real). In particular, it highlights how generic learning objectives are differently exploited in the reviewed algorithms. Finally, it discusses evaluation methods to assess the representation learned and summarizes current and future lines of research. |
| Author | Filliat, David Goudou, Jean-Frano̧is Díaz-Rodríguez, Natalia Lesort, Timothée |
| Author_xml | – sequence: 1 givenname: Timothée surname: Lesort fullname: Lesort, Timothée email: timothee.lesort@thalesgroup.com organization: Vision Lab, Thales, Theresis, Palaiseau, France – sequence: 2 givenname: Natalia orcidid: 0000-0003-3362-9326 surname: Díaz-Rodríguez fullname: Díaz-Rodríguez, Natalia email: natalia.diaz@ensta-paristech.fr organization: U2IS, ENSTA ParisTech, Inria FLOWERS team, Universite Paris Saclay, Palaiseau, France – sequence: 3 givenname: Jean-Frano̧is surname: Goudou fullname: Goudou, Jean-Frano̧is email: jean-francois.goudou@thalesgroup.com organization: Vision Lab, Thales, Theresis, Palaiseau, France – sequence: 4 givenname: David surname: Filliat fullname: Filliat, David email: david.filliat@ensta.fr organization: U2IS, ENSTA ParisTech, Inria FLOWERS team, Universite Paris Saclay, Palaiseau, France |
| BackLink | https://www.ncbi.nlm.nih.gov/pubmed/30268059$$D View this record in MEDLINE/PubMed https://hal.science/hal-01858558$$DView record in HAL |
| BookMark | eNqFkU1v1DAURS1URKeFf4BQlrBI8FccuwukUQW00khdFNaW8_ICHmXswc4M6r_Ho7QsWNCVZevcK_ncC3IWYkBC3jLaMMrUx20T8BBwbjhluqFdQ6l6QVZMd6bmneZnZEW1EbWimp6Ti5y3tBBailfkXFCuNG3Niqj72c1YJdwnzBjKxcdQTehS8OFHNcZUQQxzitNVtQ5VPGI6evz9mrwc3ZTxzeN5Sb5_-fzt-qbe3H29vV5vapCKz7VhSiAXLfRGq4GzrgctoBsZAIwd00pKMwoJDKHXQjmJBjjTVIuh7TsuxSX5sPT-dJPdJ79z6cFG5-3NemNPb-XvrW5bfWSFfb-w-xR_HTDPducz4DS5gPGQLWdMKmOU4AV994ge-h0Of5ufvBTgagEgxZwTjhb84mZOzk-WUXsawW7tMoI9jWBpZ4viEpb_hJ_6n4l9WmJYhBbJyWbwGAAHnxBmO0T__4I_BHqg9w |
| CitedBy_id | crossref_primary_10_1109_LRA_2022_3192209 crossref_primary_10_1016_j_inffus_2019_12_012 crossref_primary_10_1088_2632_2153_ac9ae8 crossref_primary_10_3390_a17020060 crossref_primary_10_1109_TRO_2019_2959445 crossref_primary_10_20965_jaciii_2022_p0562 crossref_primary_10_3390_math9212689 crossref_primary_10_1016_j_neubiorev_2019_02_008 crossref_primary_10_1109_TCSVT_2020_2987562 crossref_primary_10_2139_ssrn_3785547 crossref_primary_10_1016_j_neuron_2020_11_021 crossref_primary_10_3390_brainsci13101435 crossref_primary_10_1016_j_neucom_2019_10_124 crossref_primary_10_53759_9852_JRS202301013 crossref_primary_10_1109_TG_2023_3302694 crossref_primary_10_1016_j_neucom_2022_09_059 crossref_primary_10_1109_ACCESS_2021_3056625 crossref_primary_10_1109_LRA_2021_3068639 crossref_primary_10_1109_TCDS_2022_3152383 crossref_primary_10_1109_TCDS_2022_3156664 crossref_primary_10_1029_2021WR031041 crossref_primary_10_1016_j_ifacol_2021_04_227 crossref_primary_10_1016_j_neunet_2020_06_003 crossref_primary_10_1016_j_jclepro_2023_138472 crossref_primary_10_1016_j_autcon_2024_105396 crossref_primary_10_1016_j_ijggc_2024_104262 crossref_primary_10_1016_j_inffus_2019_12_004 crossref_primary_10_1029_2020WR029329 crossref_primary_10_1109_TIE_2024_3395770 crossref_primary_10_1103_PhysRevResearch_5_023023 crossref_primary_10_1111_exsy_13667 crossref_primary_10_3389_frobt_2019_00123 crossref_primary_10_1007_s11633_023_1464_2 crossref_primary_10_3390_make5040091 crossref_primary_10_3390_s22176504 crossref_primary_10_1016_j_datak_2019_06_004 crossref_primary_10_1109_ACCESS_2023_3274675 crossref_primary_10_1109_TITS_2021_3054625 crossref_primary_10_3390_app10175902 crossref_primary_10_7210_jrsj_39_575 crossref_primary_10_3390_app10249013 crossref_primary_10_1049_cth2_12761 crossref_primary_10_1109_TIM_2023_3246509 crossref_primary_10_1016_j_neunet_2024_106741 crossref_primary_10_1007_s10994_024_06547_6 crossref_primary_10_1016_j_neunet_2024_106347 crossref_primary_10_1109_TCDS_2022_3196179 crossref_primary_10_1016_j_inffus_2023_101805 crossref_primary_10_1007_s11042_023_15361_6 crossref_primary_10_1007_s40435_024_01407_6 crossref_primary_10_1109_TAI_2023_3283488 crossref_primary_10_1002_ece3_10747 crossref_primary_10_3389_fevo_2021_681704 crossref_primary_10_1080_01691864_2023_2221715 crossref_primary_10_1109_TPAMI_2025_3529264 crossref_primary_10_1109_TBME_2021_3054413 crossref_primary_10_1109_TCDS_2022_3187186 crossref_primary_10_1109_TRO_2019_2958211 crossref_primary_10_1063_5_0174128 crossref_primary_10_3389_frobt_2022_762051 crossref_primary_10_1080_01691864_2022_2029720 crossref_primary_10_1063_5_0177005 crossref_primary_10_1007_s13218_021_00703_z crossref_primary_10_1016_j_artint_2024_104100 crossref_primary_10_1002_ese3_1304 crossref_primary_10_1061__ASCE_AS_1943_5525_0001335 crossref_primary_10_1109_LRA_2022_3150511 crossref_primary_10_1016_j_inffus_2020_01_005 crossref_primary_10_1109_TIM_2024_3470030 crossref_primary_10_1038_s41598_022_25362_4 crossref_primary_10_1109_ACCESS_2024_3425837 crossref_primary_10_1088_1742_5468_ab3455 crossref_primary_10_3390_math12020214 crossref_primary_10_1016_j_knosys_2024_112103 crossref_primary_10_1016_j_jcp_2019_05_041 crossref_primary_10_1080_01691864_2023_2244568 crossref_primary_10_1007_s12559_020_09784_8 crossref_primary_10_1007_s11227_021_03784_7 crossref_primary_10_1007_s11740_023_01209_3 crossref_primary_10_1016_j_tins_2024_10_005 crossref_primary_10_1109_LRA_2024_3371291 crossref_primary_10_1186_s42467_021_00014_x crossref_primary_10_1016_j_knosys_2020_106685 crossref_primary_10_3390_app112110337 crossref_primary_10_1371_journal_pcbi_1012568 crossref_primary_10_1016_j_engappai_2024_109131 crossref_primary_10_1080_01691864_2023_2225232 crossref_primary_10_1016_j_engappai_2023_107496 crossref_primary_10_1088_1741_4326_ad5a1d crossref_primary_10_1108_RIA_10_2023_0146 crossref_primary_10_1109_MRA_2020_2983649 crossref_primary_10_1038_s44222_024_00177_2 crossref_primary_10_1016_j_compchemeng_2024_108849 |
| Cites_doi | 10.1109/TEVC.2006.890271 10.1109/TRO.2017.2721939 10.1613/jair.3912 10.1016/j.neucom.2012.05.013 10.1109/TCIAIG.2012.2188528 10.1007/s10514-015-9459-7 10.1109/TNN.1998.712192 10.1162/089976602317318938 10.1038/nature14236 10.1162/neco.2006.18.7.1527 10.1109/IJCNN.2018.8489075 10.1016/j.neucom.2015.08.104 |
| ContentType | Journal Article |
| Copyright | 2018 Elsevier Ltd Copyright © 2018 Elsevier Ltd. All rights reserved. Distributed under a Creative Commons Attribution 4.0 International License |
| Copyright_xml | – notice: 2018 Elsevier Ltd – notice: Copyright © 2018 Elsevier Ltd. All rights reserved. – notice: Distributed under a Creative Commons Attribution 4.0 International License |
| DBID | AAYXX CITATION CGR CUY CVF ECM EIF NPM 7X8 1XC VOOES |
| DOI | 10.1016/j.neunet.2018.07.006 |
| DatabaseName | CrossRef Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE PubMed MEDLINE - Academic Hyper Article en Ligne (HAL) Hyper Article en Ligne (HAL) (Open Access) |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) MEDLINE - Academic |
| DatabaseTitleList | MEDLINE MEDLINE - Academic |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Computer Science |
| EISSN | 1879-2782 |
| EndPage | 392 |
| ExternalDocumentID | oai_HAL_hal_01858558v1 30268059 10_1016_j_neunet_2018_07_006 S0893608018302053 |
| Genre | Journal Article Review |
| GroupedDBID | --- --K --M -~X .DC .~1 0R~ 123 186 1B1 1RT 1~. 1~5 29N 4.4 457 4G. 53G 5RE 5VS 6TJ 7-5 71M 8P~ 9JM 9JN AABNK AACTN AADPK AAEDT AAEDW AAIAV AAIKJ AAKOC AALRI AAOAW AAQFI AAQXK AAXLA AAXUO AAYFN ABAOU ABBOA ABCQJ ABEFU ABFNM ABFRF ABHFT ABIVO ABJNI ABLJU ABMAC ABXDB ABYKQ ACAZW ACDAQ ACGFO ACGFS ACIUM ACNNM ACRLP ACZNC ADBBV ADEZE ADGUI ADJOM ADMUD ADRHT AEBSH AECPX AEFWE AEKER AENEX AFKWA AFTJW AFXIZ AGHFR AGUBO AGWIK AGYEJ AHHHB AHJVU AHZHX AIALX AIEXJ AIKHN AITUG AJBFU AJOXV ALMA_UNASSIGNED_HOLDINGS AMFUW AMRAJ AOUOD ARUGR ASPBG AVWKF AXJTR AZFZN BJAXD BKOJK BLXMC CS3 DU5 EBS EFJIC EFLBG EJD EO8 EO9 EP2 EP3 F0J F5P FDB FEDTE FGOYB FIRID FNPLU FYGXN G-2 G-Q G8K GBLVA GBOLZ HLZ HMQ HVGLF HZ~ IHE J1W JJJVA K-O KOM KZ1 LG9 LMP M2V M41 MHUIS MO0 MOBAO MVM N9A O-L O9- OAUVE OZT P-8 P-9 P2P PC. Q38 R2- RIG ROL RPZ SBC SCC SDF SDG SDP SES SEW SNS SPC SPCBC SSN SST SSV SSW SSZ T5K TAE UAP UNMZH VOH WUQ XPP ZMT ~G- AATTM AAXKI AAYWO AAYXX ABDPE ABWVN ACRPL ACVFH ADCNI ADNMO AEIPS AEUPX AFJKZ AFPUW AGCQF AGQPQ AGRNS AIGII AIIUN AKBMS AKRWK AKYEP ANKPU APXCP BNPGV CITATION SSH CGR CUY CVF ECM EIF NPM PKN 7X8 EFKBS 1XC VOOES |
| ID | FETCH-LOGICAL-c462t-9163e235cb986d217bc83c7f1cccf7186449f34c1ecb836a4e9c218083d5b7243 |
| IEDL.DBID | AIKHN |
| ISSN | 0893-6080 1879-2782 |
| IngestDate | Wed Jun 11 06:20:46 EDT 2025 Thu Sep 04 21:15:21 EDT 2025 Wed Feb 19 02:34:15 EST 2025 Tue Jul 01 01:24:32 EDT 2025 Thu Apr 24 23:02:20 EDT 2025 Fri Feb 23 02:46:10 EST 2024 |
| IsDoiOpenAccess | true |
| IsOpenAccess | true |
| IsPeerReviewed | true |
| IsScholarly | true |
| Keywords | State representation learning Learning disentangled representations Disentanglement of control factors Robotics Low dimensional embedding learning Reinforcement learning Reinforcement Learning State Representation Learning Low Dimensional Embedding Learning Learning Disentangled Representations |
| Language | English |
| License | Copyright © 2018 Elsevier Ltd. All rights reserved. Distributed under a Creative Commons Attribution 4.0 International License: http://creativecommons.org/licenses/by/4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c462t-9163e235cb986d217bc83c7f1cccf7186449f34c1ecb836a4e9c218083d5b7243 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 ObjectType-Review-3 content type line 23 |
| ORCID | 0000-0003-3362-9326 0000-0002-5739-1618 |
| OpenAccessLink | https://hal.science/hal-01858558 |
| PMID | 30268059 |
| PQID | 2114699632 |
| PQPubID | 23479 |
| PageCount | 14 |
| ParticipantIDs | hal_primary_oai_HAL_hal_01858558v1 proquest_miscellaneous_2114699632 pubmed_primary_30268059 crossref_citationtrail_10_1016_j_neunet_2018_07_006 crossref_primary_10_1016_j_neunet_2018_07_006 elsevier_sciencedirect_doi_10_1016_j_neunet_2018_07_006 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | December 2018 2018-12-00 2018-Dec 20181201 2018-12 |
| PublicationDateYYYYMMDD | 2018-12-01 |
| PublicationDate_xml | – month: 12 year: 2018 text: December 2018 |
| PublicationDecade | 2010 |
| PublicationPlace | United States |
| PublicationPlace_xml | – name: United States |
| PublicationTitle | Neural networks |
| PublicationTitleAlternate | Neural Netw |
| PublicationYear | 2018 |
| Publisher | Elsevier Ltd Elsevier |
| Publisher_xml | – name: Elsevier Ltd – name: Elsevier |
| References | Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. ArXiv e-prints. Mnih, V., Agapiou, J., Osindero, S., Graves, A., Vinyals, O., & Kavukcuoglu, K. et al. (2016). Strategic attentive writer for learning macro-actions. ArXiv Preprint Pinto, L., Gandhi, D., Han, Y., Park, Y., & Gupta, A. (2016). The curious robot: Learning visual representations via physical interactions. CoRR abs/1604.01360. URL Agrawal, P., Nair, A., Abbeel, P., Malik, J., & Levine, S. (2016). Learning to Poke by Poking: Experiential Learning of Intuitive Physics. CoRR abs/1606.07419. Donahue, J., Krähenbühl, P., & Darrell, T. (2016). Adversarial feature learning. CoRR abs/1605.09782. Bousmalis, K., Irpan, A., Wohlhart, P., Bai, Y., Kelcey, M., & Kalakrishnan, M. et al. (2017). Using simulation and domain adaptation to improve efficiency of deep robotic grasping. ArXiv Preprint Jimenez Rezende, D., Mohamed, S., & Wierstra, D. (2014). Stochastic backpropagation and approximate inference in deep generative models. ArXiv e-prints Assael, Wahlström, Schön, Deisenroth (b4) 2015 Bengio, Y., Courville, A. C., & Vincent, P. (2012). Unsupervised feature learning and deep learning: A review and new perspectives. CoRR abs/1206.5538. URL Finn, C., Tan, X. Y., Duan, Y., Darrell, T., Levine, S., & Abbeel, P. (2015). Deep spatial autoencoders for visuomotor learning. CoRR abs/1509.06113. URL Achille, A., & Soatto, S. (2017). A Separation Principle for Control in the Age of Deep Learning. ArXiv e-prints Kompella, V. R., Luciw, M. D., & Schmidhuber, J. (2011). Incremental slow feature analysis: Adaptive and episodic learning from high-dimensional input streams. CoRR abs/1112.2113. URL Parisi, Ramstedt, Peters (b55) 2017 Conti, E., Madhavan, V., Petroski Such, F., Lehman, J., Stanley, K. O., & Clune, J. (2017). Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. ArXiv e-prints. Péré, Forestier, Oudeyer, Sigaud (b58) 2018 Chen, Duan, Houthooft, Schulman, Sutskever, Abbeel (b12) 2016 Jonschkowski, R., Hafner, R., Scholz, J., & Riedmiller, M. A. (2017). PVEs: Position-velocity encoders for unsupervised learning of structured state representations. CoRR abs/1705.09805. URL Hinton, Osindero, Teh (b31) 2006; 18 Krishnan, R. G., Shalit, U., & Sontag, D. (2015). Deep kalman filters. ArXiv e-prints. Goodman, B., & Flaxman, S. (2016). European Union regulations on algorithmic decision-making and a” right to explanation”. arXiv preprint Deisenroth, Rasmussen (b17) 2011 Oh, J., Singh, S., & Lee, H. (2017). Value prediction network. ArXiv e-prints. Chopra, Hadsell, LeCun (b13) 2005 Munk, Kober, Babuska (b52) 2016 Lipton, Z. C. (2016). The mythos of model interpretability. ArXiv e-prints. Watter, Springenberg, Boedecker, Riedmiller (b71) 2015 Yang, X., Ramesh, P., Chitta, R., Madhvanath, S., Bernal, E. A., & Luo, J. (2017). Deep multimodal representation learning from temporal data. CoRR abs/1704.03152. Goroshin, R., Mathieu, M., & LeCun, Y. (2015). Learning to linearize under uncertainty. CoRR abs/1506.03011. URL Indyk (b33) 2001 van Hoof, Chen, Karl, van der Smagt, Peters (b32) 2016 Pathak, Agrawal, Efros, Darrell (b56) 2017 Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., & Botvinick, M. et al. (2016). beta-vae: Learning basic visual concepts with a constrained variational framework. Wang, He, Prokhorov (b69) 2012; vol. 13 Ha, D., & Schmidhuber, J. (2018). World models. ArXiv e-prints Stulp, Sigaud (b62) 2013; 4 Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016). Building machines that learn and think like people. ArXiv e-prints. Wahlström, N., Schön, T. B., & Deisenroth, M. P. (2015). From pixels to torques: policy learning with deep dynamical models. ArXiv e-prints. Vincent, Larochelle, Lajoie, Bengio, Manzagol (b67) 2010; 11 . Lesort, T., Seurin, M., Li, X., Díaz-Rodríguez, N., & Filliat, D. (2017). Unsupervised state representation learning with robotic priors: a robustness benchmark. CoRR abs/1709.05185 Fodor, I. K. (2002). A survey of dimension reduction techniques, Tech. rep., Lawrence Livermore National Lab., CA (US). Shelhamer, E., Mahmoudieh, P., Argus, M., & Darrell, T. (2017). Loss is its own Reward: Self-Supervision for Reinforcement Learning. arXiv preprint Wiskott, Sejnowski (b72) 2002; 14 Curran, W., Brys, T., Aha, D., Taylor, M., & Smart, W. D. (2016). Dimensionality reduced reinforcement learning for assistive robots. Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., & Arjovsky, M. et al. (2016). Adversarially learned inference. arXiv preprint Vincent, Larochelle, Bengio, Manzagol (b66) 2008 Zhang, Satija, Pineau (b75) 2018 Böhmer, Springenberg, Boedecker, Riedmiller, Obermayer (b10) 2015 Magrans de Abril, I., & Kanai, R. (2018) Curiosity-driven reinforcement learning with homeostatic regulation. ArXiv e-prints. Curran, W., Brys, T., Taylor, M., & Smart, W. (2015). Using PCA to efficiently represent state spaces. ArXiv e-prints. Mattner, Lange, Riedmiller (b48) 2012 Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., & Meger, D. (2017). Deep reinforcement learning that matters. CoRR abs/1709.06560. Karl, M., Soelch, M., Bayer, J., & van der Smagt, P. (2016). Deep variational bayes filters: unsupervised learning of state space models from raw data. ArXiv e-prints. Sermanet, P., Lynch, C., Hsu, J., & Levine, S. (2017). Time-contrastive networks: self-supervised learning from multi-view observation. CoRR abs/1704.06888. URL URL Higgins, I., Pal, A., Rusu, A. A., Matthey, L., Burgess, C. P., & Pritzel, A. et al. (2017). DARLA: Improving Zero-Shot Transfer in Reinforcement Learning. ArXiv e-prints. Sutton, R. S. (1998). Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013). The arcade learning environment: An evaluation platform for general agents. Jonschkowski, Brock (b35) 2015; 39 Oudeyer, Kaplan, Hafner (b54) 2007; 11 Wang, Yao, Zhao (b70) 2016; 184 Thomas, V., Pondard, J., Bengio, E., Sarfati, M., Beaudoin, P., & Meurs, M. et al. (2017). Independently controllable factors. CoRR abs/1708.01289. Beattie, C., Leibo, J. Z., Teplyashin, D., Ward, T., Wainwright, M., & Küttler, H. et al. (2016). DeepMind Lab. CoRR abs/1612.03801. Klyubin, Polani, Nehaniv (b40) 2005 Mnih, Kavukcuoglu, Silver, Rusu, Veness, Bellemare (b50) 2015; 518 Engel, Szabo, Volkinshtein (b21) 2006 Zhang, Ren, Zhang (b74) 2012; 97 Alvernaz, S., & Togelius, J. (2017). Autoencoder-augmented Neuroevolution for Visual Doom Playing. ArXiv e-prints Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., & Ozair, S. et al. (2014). Generative adversarial nets, pp. 26722680. URL Mouret, J., Koos, S., & Doncieux, S. (2013). Crossing the reality gap: a short introduction to the transferability approach. CoRR abs/1307.1870. Bohg, Hausman, Sankaran, Brock, Kragic, Schaal (b8) 2017; 33 Karakovskiy (b37) 2012; 4 Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., & Tassa, Y. et al. (2015). Continuous control with deep reinforcement learning. CoRR abs/1509.02971. Duan, W. (2017). Learning state representations for robotic control (M. Thesis). URL Tassa, Y., Doron, Y., Muldal, A., Erez, T., Li, Y., & de Las Casas, D. et al. (2018). DeepMind control suite. ArXiv e-prints. Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., & Tang, J. et al. (2016). OpenAI Gym. CoRR abs/1606.01540. Rusu, A. A., Rabinowitz, N. C., Desjardins, G., Soyer, H., Kirkpatrick, J., & Kavukcuoglu, K. et al. (2016). Progressive neural networks CoRR abs/1606.04671. URL 10.1016/j.neunet.2018.07.006_b1 10.1016/j.neunet.2018.07.006_b3 10.1016/j.neunet.2018.07.006_b2 Engel (10.1016/j.neunet.2018.07.006_b21) 2006 10.1016/j.neunet.2018.07.006_b9 10.1016/j.neunet.2018.07.006_b47 10.1016/j.neunet.2018.07.006_b46 10.1016/j.neunet.2018.07.006_b45 10.1016/j.neunet.2018.07.006_b44 10.1016/j.neunet.2018.07.006_b5 10.1016/j.neunet.2018.07.006_b43 10.1016/j.neunet.2018.07.006_b42 10.1016/j.neunet.2018.07.006_b7 10.1016/j.neunet.2018.07.006_b41 10.1016/j.neunet.2018.07.006_b6 Chen (10.1016/j.neunet.2018.07.006_b12) 2016 Böhmer (10.1016/j.neunet.2018.07.006_b10) 2015 Wang (10.1016/j.neunet.2018.07.006_b69) 2012; vol. 13 10.1016/j.neunet.2018.07.006_b49 Hinton (10.1016/j.neunet.2018.07.006_b31) 2006; 18 Chopra (10.1016/j.neunet.2018.07.006_b13) 2005 Oudeyer (10.1016/j.neunet.2018.07.006_b54) 2007; 11 Wiskott (10.1016/j.neunet.2018.07.006_b72) 2002; 14 Jonschkowski (10.1016/j.neunet.2018.07.006_b35) 2015; 39 10.1016/j.neunet.2018.07.006_b14 10.1016/j.neunet.2018.07.006_b57 Deisenroth (10.1016/j.neunet.2018.07.006_b17) 2011 10.1016/j.neunet.2018.07.006_b11 10.1016/j.neunet.2018.07.006_b53 10.1016/j.neunet.2018.07.006_b51 Assael (10.1016/j.neunet.2018.07.006_b4) 2015 10.1016/j.neunet.2018.07.006_b19 10.1016/j.neunet.2018.07.006_b18 10.1016/j.neunet.2018.07.006_b16 Zhang (10.1016/j.neunet.2018.07.006_b74) 2012; 97 Bohg (10.1016/j.neunet.2018.07.006_b8) 2017; 33 10.1016/j.neunet.2018.07.006_b15 10.1016/j.neunet.2018.07.006_b59 Mnih (10.1016/j.neunet.2018.07.006_b50) 2015; 518 10.1016/j.neunet.2018.07.006_b61 10.1016/j.neunet.2018.07.006_b60 10.1016/j.neunet.2018.07.006_b25 10.1016/j.neunet.2018.07.006_b24 10.1016/j.neunet.2018.07.006_b68 10.1016/j.neunet.2018.07.006_b23 Péré (10.1016/j.neunet.2018.07.006_b58) 2018 10.1016/j.neunet.2018.07.006_b22 10.1016/j.neunet.2018.07.006_b65 10.1016/j.neunet.2018.07.006_b20 10.1016/j.neunet.2018.07.006_b64 10.1016/j.neunet.2018.07.006_b63 10.1016/j.neunet.2018.07.006_b29 10.1016/j.neunet.2018.07.006_b28 Wang (10.1016/j.neunet.2018.07.006_b70) 2016; 184 10.1016/j.neunet.2018.07.006_b27 Parisi (10.1016/j.neunet.2018.07.006_b55) 2017 10.1016/j.neunet.2018.07.006_b26 van Hoof (10.1016/j.neunet.2018.07.006_b32) 2016 Vincent (10.1016/j.neunet.2018.07.006_b66) 2008 Indyk (10.1016/j.neunet.2018.07.006_b33) 2001 Zhang (10.1016/j.neunet.2018.07.006_b75) 2018 Pathak (10.1016/j.neunet.2018.07.006_b56) 2017 Klyubin (10.1016/j.neunet.2018.07.006_b40) 2005 10.1016/j.neunet.2018.07.006_b36 10.1016/j.neunet.2018.07.006_b34 Stulp (10.1016/j.neunet.2018.07.006_b62) 2013; 4 Karakovskiy (10.1016/j.neunet.2018.07.006_b37) 2012; 4 10.1016/j.neunet.2018.07.006_b30 10.1016/j.neunet.2018.07.006_b73 Mattner (10.1016/j.neunet.2018.07.006_b48) 2012 Watter (10.1016/j.neunet.2018.07.006_b71) 2015 10.1016/j.neunet.2018.07.006_b39 10.1016/j.neunet.2018.07.006_b38 Munk (10.1016/j.neunet.2018.07.006_b52) 2016 Vincent (10.1016/j.neunet.2018.07.006_b67) 2010; 11 |
| References_xml | – year: 2017 ident: b56 article-title: Curiosity-driven exploration by self-supervised prediction publication-title: ICML – reference: Yang, X., Ramesh, P., Chitta, R., Madhvanath, S., Bernal, E. A., & Luo, J. (2017). Deep multimodal representation learning from temporal data. CoRR abs/1704.03152. – volume: 39 start-page: 407 year: 2015 end-page: 428 ident: b35 article-title: Learning state representations with robotic priors publication-title: Autonomous Robots – reference: Higgins, I., Pal, A., Rusu, A. A., Matthey, L., Burgess, C. P., & Pritzel, A. et al. (2017). DARLA: Improving Zero-Shot Transfer in Reinforcement Learning. ArXiv e-prints. – reference: Fodor, I. K. (2002). A survey of dimension reduction techniques, Tech. rep., Lawrence Livermore National Lab., CA (US). – reference: Beattie, C., Leibo, J. Z., Teplyashin, D., Ward, T., Wainwright, M., & Küttler, H. et al. (2016). DeepMind Lab. CoRR abs/1612.03801. – start-page: 347 year: 2006 end-page: 354 ident: b21 article-title: Learning to control an octopus arm with Gaussian process temporal difference methods publication-title: Advances in neural information processing systems – reference: Bengio, Y., Courville, A. C., & Vincent, P. (2012). Unsupervised feature learning and deep learning: A review and new perspectives. CoRR abs/1206.5538. URL – volume: 14 start-page: 715 year: 2002 end-page: 770 ident: b72 article-title: Slow feature analysis: Unsupervised learning of invariances publication-title: Neural Computation – volume: 97 start-page: 251 year: 2012 end-page: 266 ident: b74 article-title: A new embedding quality assessment method for manifold learning publication-title: Neurocomputing – reference: . URL – reference: Kingma, D. P., & Welling, M. (2013). Auto-encoding variational bayes. ArXiv e-prints. – reference: Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., & Ozair, S. et al. (2014). Generative adversarial nets, pp. 26722680. URL – start-page: 2746 year: 2015 end-page: 2754 ident: b71 article-title: Embed to control: A locally linear latent dynamics model for control from raw images publication-title: Advances in neural information processing systems 28 – reference: Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., & Tassa, Y. et al. (2015). Continuous control with deep reinforcement learning. CoRR abs/1509.02971. – reference: Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., & Botvinick, M. et al. (2016). beta-vae: Learning basic visual concepts with a constrained variational framework. – reference: Karl, M., Soelch, M., Bayer, J., & van der Smagt, P. (2016). Deep variational bayes filters: unsupervised learning of state space models from raw data. ArXiv e-prints. – reference: Sermanet, P., Lynch, C., Hsu, J., & Levine, S. (2017). Time-contrastive networks: self-supervised learning from multi-view observation. CoRR abs/1704.06888. URL – volume: 11 start-page: 3371 year: 2010 end-page: 3408 ident: b67 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research (JMLR) – reference: Thomas, V., Pondard, J., Bengio, E., Sarfati, M., Beaudoin, P., & Meurs, M. et al. (2017). Independently controllable factors. CoRR abs/1708.01289. – reference: Mnih, V., Agapiou, J., Osindero, S., Graves, A., Vinyals, O., & Kavukcuoglu, K. et al. (2016). Strategic attentive writer for learning macro-actions. ArXiv Preprint – reference: Brockman, G., Cheung, V., Pettersson, L., Schneider, J., Schulman, J., & Tang, J. et al. (2016). OpenAI Gym. CoRR abs/1606.01540. – year: 2015 ident: b4 article-title: Data-efficient learning of feedback policies from image pixels using deep dynamical models publication-title: NIPS deep reinforcement learning workshop – start-page: 539 year: 2005 end-page: 546 ident: b13 article-title: Learning a similarity metric discriminatively, with application to face verification publication-title: 2005 IEEE computer society conference on computer vision and pattern recognition, vol. 1 – reference: Oh, J., Singh, S., & Lee, H. (2017). Value prediction network. ArXiv e-prints. – reference: Conti, E., Madhavan, V., Petroski Such, F., Lehman, J., Stanley, K. O., & Clune, J. (2017). Improving exploration in evolution strategies for deep reinforcement learning via a population of novelty-seeking agents. ArXiv e-prints. – volume: 4 start-page: 49 year: 2013 end-page: 61 ident: b62 article-title: Robot skill learning: From reinforcement learning to evolution strategies publication-title: Paladyn – reference: Alvernaz, S., & Togelius, J. (2017). Autoencoder-augmented Neuroevolution for Visual Doom Playing. ArXiv e-prints – reference: Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., & Arjovsky, M. et al. (2016). Adversarially learned inference. arXiv preprint – start-page: 4667 year: 2016 end-page: 4673 ident: b52 article-title: Learning state representation for deep actor-critic control publication-title: Proceedings of the 55th conference on decision and control (CDC) – start-page: 2172 year: 2016 end-page: 2180 ident: b12 article-title: Infogan: Interpretable representation learning by information maximizing generative adversarial nets publication-title: Advances in neural information processing systems – reference: Henderson, P., Islam, R., Bachman, P., Pineau, J., Precup, D., & Meger, D. (2017). Deep reinforcement learning that matters. CoRR abs/1709.06560. – reference: Lipton, Z. C. (2016). The mythos of model interpretability. ArXiv e-prints. – start-page: 1096 year: 2008 end-page: 1103 ident: b66 article-title: Extracting and composing robust features with denoising autoencoders publication-title: Proceedings of the 25th international conference on machine learning – reference: Jimenez Rezende, D., Mohamed, S., & Wierstra, D. (2014). Stochastic backpropagation and approximate inference in deep generative models. ArXiv e-prints – reference: Donahue, J., Krähenbühl, P., & Darrell, T. (2016). Adversarial feature learning. CoRR abs/1605.09782. – volume: 11 start-page: 265 year: 2007 end-page: 286 ident: b54 article-title: Intrinsic motivation systems for autonomous mental development publication-title: IEEE Transactions on Evolutionary Computation – reference: Curran, W., Brys, T., Aha, D., Taylor, M., & Smart, W. D. (2016). Dimensionality reduced reinforcement learning for assistive robots. – reference: Finn, C., Tan, X. Y., Duan, Y., Darrell, T., Levine, S., & Abbeel, P. (2015). Deep spatial autoencoders for visuomotor learning. CoRR abs/1509.06113. URL – reference: Bellemare, M. G., Naddaf, Y., Veness, J., & Bowling, M. (2013). The arcade learning environment: An evaluation platform for general agents. – reference: Krishnan, R. G., Shalit, U., & Sontag, D. (2015). Deep kalman filters. ArXiv e-prints. – reference: Mouret, J., Koos, S., & Doncieux, S. (2013). Crossing the reality gap: a short introduction to the transferability approach. CoRR abs/1307.1870. – reference: Sutton, R. S. (1998). – volume: vol. 13 start-page: 120 year: 2012 end-page: 127 ident: b69 article-title: A folded neural network autoencoder for dimensionality reduction. publication-title: INNS-WC – year: 2018 ident: b58 article-title: Unsupervised learning of goal spaces for intrinsically motivated goal exploration publication-title: International conference on learning representations – reference: Ha, D., & Schmidhuber, J. (2018). World models. ArXiv e-prints – reference: Kompella, V. R., Luciw, M. D., & Schmidhuber, J. (2011). Incremental slow feature analysis: Adaptive and episodic learning from high-dimensional input streams. CoRR abs/1112.2113. URL – reference: Tassa, Y., Doron, Y., Muldal, A., Erez, T., Li, Y., & de Las Casas, D. et al. (2018). DeepMind control suite. ArXiv e-prints. – reference: Curran, W., Brys, T., Taylor, M., & Smart, W. (2015). Using PCA to efficiently represent state spaces. ArXiv e-prints. – volume: 518 start-page: 529 year: 2015 end-page: 533 ident: b50 article-title: Human-level control through deep reinforcement learning publication-title: Nature – reference: Shelhamer, E., Mahmoudieh, P., Argus, M., & Darrell, T. (2017). Loss is its own Reward: Self-Supervision for Reinforcement Learning. arXiv preprint – start-page: 126 year: 2012 end-page: 133 ident: b48 article-title: Learn to swing up and balance a real pole based on raw visual input data publication-title: Neural information processing - 19th international conference, ICONIP 2012, Doha, Qatar, November 12-15, 2012, Proceedings, Part V – reference: Pinto, L., Gandhi, D., Han, Y., Park, Y., & Gupta, A. (2016). The curious robot: Learning visual representations via physical interactions. CoRR abs/1604.01360. URL – volume: 184 start-page: 232 year: 2016 end-page: 242 ident: b70 article-title: Auto-encoder based dimensionality reduction publication-title: Neurocomput – reference: Lake, B. M., Ullman, T. D., Tenenbaum, J. B., & Gershman, S. J. (2016). Building machines that learn and think like people. ArXiv e-prints. – reference: Achille, A., & Soatto, S. (2017). A Separation Principle for Control in the Age of Deep Learning. ArXiv e-prints – start-page: 3928 year: 2016 end-page: 3934 ident: b32 article-title: Stable reinforcement learning with autoencoders for tactile and visual data publication-title: 2016 IEEE/RSJ international conference on intelligent robots and systems (IROS) – reference: Agrawal, P., Nair, A., Abbeel, P., Malik, J., & Levine, S. (2016). Learning to Poke by Poking: Experiential Learning of Intuitive Physics. CoRR abs/1606.07419. – start-page: 128 year: 2005 end-page: 135 ident: b40 article-title: Empowerment: A universal agent-centric measure of control publication-title: Evolutionary computation, 2005. The 2005 IEEE congress on, vol. 1 – volume: 4 start-page: 55 year: 2012 end-page: 67 ident: b37 article-title: The mario AI benchmark and competitions publication-title: IEEE Transactions on Computational Intelligence and AI in Games – reference: Lesort, T., Seurin, M., Li, X., Díaz-Rodríguez, N., & Filliat, D. (2017). Unsupervised state representation learning with robotic priors: a robustness benchmark. CoRR abs/1709.05185 – volume: 33 start-page: 1273 year: 2017 end-page: 1291 ident: b8 article-title: Interactive perception: Leveraging action in perception and perception in action publication-title: IEEE Transactions on Robotics – year: 2017 ident: b55 article-title: Goal-driven dimensionality reduction for reinforcement learning publication-title: Proceedings of the IEEE/RSJ conference on intelligent robots and systems (IROS) – reference: Goroshin, R., Mathieu, M., & LeCun, Y. (2015). Learning to linearize under uncertainty. CoRR abs/1506.03011. URL – reference: Jonschkowski, R., Hafner, R., Scholz, J., & Riedmiller, M. A. (2017). PVEs: Position-velocity encoders for unsupervised learning of structured state representations. CoRR abs/1705.09805. URL – year: 2018 ident: b75 article-title: Decoupling dynamics and reward for transfer learning publication-title: Proceedings of the 6th international conference on learning representations (ICLR) workshops – reference: . – reference: Duan, W. (2017). Learning state representations for robotic control (M. Thesis). URL – reference: Goodman, B., & Flaxman, S. (2016). European Union regulations on algorithmic decision-making and a” right to explanation”. arXiv preprint – reference: Wahlström, N., Schön, T. B., & Deisenroth, M. P. (2015). From pixels to torques: policy learning with deep dynamical models. ArXiv e-prints. – volume: 18 start-page: 1527 year: 2006 end-page: 1554 ident: b31 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation – reference: Rusu, A. A., Rabinowitz, N. C., Desjardins, G., Soyer, H., Kirkpatrick, J., & Kavukcuoglu, K. et al. (2016). Progressive neural networks CoRR abs/1606.04671. URL – start-page: 1 year: 2015 end-page: 10 ident: b10 article-title: Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations publication-title: KI - Küstliche Intelligenz – start-page: 465 year: 2011 end-page: 472 ident: b17 article-title: PILCO: A model-based and data-efficient approach to policy search publication-title: Proceedings of the 28th international conference on international conference on machine learning – start-page: 10 year: 2001 end-page: 33 ident: b33 article-title: Algorithmic applications of low-distortion geometric embeddings publication-title: Foundations of computer science, 2001. Proceedings. 42nd IEEE symposium on – reference: Magrans de Abril, I., & Kanai, R. (2018) Curiosity-driven reinforcement learning with homeostatic regulation. ArXiv e-prints. – reference: Bousmalis, K., Irpan, A., Wohlhart, P., Bai, Y., Kelcey, M., & Kalakrishnan, M. et al. (2017). Using simulation and domain adaptation to improve efficiency of deep robotic grasping. ArXiv Preprint – year: 2018 ident: 10.1016/j.neunet.2018.07.006_b58 article-title: Unsupervised learning of goal spaces for intrinsically motivated goal exploration – ident: 10.1016/j.neunet.2018.07.006_b49 – ident: 10.1016/j.neunet.2018.07.006_b26 – ident: 10.1016/j.neunet.2018.07.006_b51 – ident: 10.1016/j.neunet.2018.07.006_b68 – start-page: 2746 year: 2015 ident: 10.1016/j.neunet.2018.07.006_b71 article-title: Embed to control: A locally linear latent dynamics model for control from raw images – ident: 10.1016/j.neunet.2018.07.006_b39 – ident: 10.1016/j.neunet.2018.07.006_b16 – ident: 10.1016/j.neunet.2018.07.006_b65 – ident: 10.1016/j.neunet.2018.07.006_b7 – ident: 10.1016/j.neunet.2018.07.006_b42 – start-page: 10 year: 2001 ident: 10.1016/j.neunet.2018.07.006_b33 article-title: Algorithmic applications of low-distortion geometric embeddings – ident: 10.1016/j.neunet.2018.07.006_b61 – ident: 10.1016/j.neunet.2018.07.006_b3 – volume: 11 start-page: 265 issue: 2 year: 2007 ident: 10.1016/j.neunet.2018.07.006_b54 article-title: Intrinsic motivation systems for autonomous mental development publication-title: IEEE Transactions on Evolutionary Computation doi: 10.1109/TEVC.2006.890271 – start-page: 1096 year: 2008 ident: 10.1016/j.neunet.2018.07.006_b66 article-title: Extracting and composing robust features with denoising autoencoders – ident: 10.1016/j.neunet.2018.07.006_b23 – start-page: 539 year: 2005 ident: 10.1016/j.neunet.2018.07.006_b13 article-title: Learning a similarity metric discriminatively, with application to face verification – volume: 33 start-page: 1273 issue: 6 year: 2017 ident: 10.1016/j.neunet.2018.07.006_b8 article-title: Interactive perception: Leveraging action in perception and perception in action publication-title: IEEE Transactions on Robotics doi: 10.1109/TRO.2017.2721939 – start-page: 3928 year: 2016 ident: 10.1016/j.neunet.2018.07.006_b32 article-title: Stable reinforcement learning with autoencoders for tactile and visual data – start-page: 126 year: 2012 ident: 10.1016/j.neunet.2018.07.006_b48 article-title: Learn to swing up and balance a real pole based on raw visual input data – ident: 10.1016/j.neunet.2018.07.006_b25 – ident: 10.1016/j.neunet.2018.07.006_b6 doi: 10.1613/jair.3912 – ident: 10.1016/j.neunet.2018.07.006_b29 – year: 2017 ident: 10.1016/j.neunet.2018.07.006_b56 article-title: Curiosity-driven exploration by self-supervised prediction – ident: 10.1016/j.neunet.2018.07.006_b46 – volume: 97 start-page: 251 year: 2012 ident: 10.1016/j.neunet.2018.07.006_b74 article-title: A new embedding quality assessment method for manifold learning publication-title: Neurocomputing doi: 10.1016/j.neucom.2012.05.013 – start-page: 128 year: 2005 ident: 10.1016/j.neunet.2018.07.006_b40 article-title: Empowerment: A universal agent-centric measure of control – ident: 10.1016/j.neunet.2018.07.006_b15 – ident: 10.1016/j.neunet.2018.07.006_b64 – start-page: 4667 year: 2016 ident: 10.1016/j.neunet.2018.07.006_b52 article-title: Learning state representation for deep actor-critic control – ident: 10.1016/j.neunet.2018.07.006_b43 – ident: 10.1016/j.neunet.2018.07.006_b60 – ident: 10.1016/j.neunet.2018.07.006_b19 – ident: 10.1016/j.neunet.2018.07.006_b36 – ident: 10.1016/j.neunet.2018.07.006_b22 – volume: 4 start-page: 55 issue: 1 year: 2012 ident: 10.1016/j.neunet.2018.07.006_b37 article-title: The mario AI benchmark and competitions publication-title: IEEE Transactions on Computational Intelligence and AI in Games doi: 10.1109/TCIAIG.2012.2188528 – ident: 10.1016/j.neunet.2018.07.006_b57 – volume: 39 start-page: 407 issue: 3 year: 2015 ident: 10.1016/j.neunet.2018.07.006_b35 article-title: Learning state representations with robotic priors publication-title: Autonomous Robots doi: 10.1007/s10514-015-9459-7 – ident: 10.1016/j.neunet.2018.07.006_b30 – ident: 10.1016/j.neunet.2018.07.006_b63 doi: 10.1109/TNN.1998.712192 – ident: 10.1016/j.neunet.2018.07.006_b1 – ident: 10.1016/j.neunet.2018.07.006_b24 – ident: 10.1016/j.neunet.2018.07.006_b28 – ident: 10.1016/j.neunet.2018.07.006_b53 – ident: 10.1016/j.neunet.2018.07.006_b34 – volume: vol. 13 start-page: 120 year: 2012 ident: 10.1016/j.neunet.2018.07.006_b69 article-title: A folded neural network autoencoder for dimensionality reduction. – ident: 10.1016/j.neunet.2018.07.006_b11 – start-page: 347 year: 2006 ident: 10.1016/j.neunet.2018.07.006_b21 article-title: Learning to control an octopus arm with Gaussian process temporal difference methods – volume: 14 start-page: 715 issue: 4 year: 2002 ident: 10.1016/j.neunet.2018.07.006_b72 article-title: Slow feature analysis: Unsupervised learning of invariances publication-title: Neural Computation doi: 10.1162/089976602317318938 – ident: 10.1016/j.neunet.2018.07.006_b9 – ident: 10.1016/j.neunet.2018.07.006_b14 – ident: 10.1016/j.neunet.2018.07.006_b18 – volume: 518 start-page: 529 issue: 7540 year: 2015 ident: 10.1016/j.neunet.2018.07.006_b50 article-title: Human-level control through deep reinforcement learning publication-title: Nature doi: 10.1038/nature14236 – year: 2017 ident: 10.1016/j.neunet.2018.07.006_b55 article-title: Goal-driven dimensionality reduction for reinforcement learning – ident: 10.1016/j.neunet.2018.07.006_b44 – ident: 10.1016/j.neunet.2018.07.006_b5 – volume: 4 start-page: 49 issue: 1 year: 2013 ident: 10.1016/j.neunet.2018.07.006_b62 article-title: Robot skill learning: From reinforcement learning to evolution strategies publication-title: Paladyn – ident: 10.1016/j.neunet.2018.07.006_b27 – volume: 18 start-page: 1527 year: 2006 ident: 10.1016/j.neunet.2018.07.006_b31 article-title: A fast learning algorithm for deep belief nets publication-title: Neural Computation doi: 10.1162/neco.2006.18.7.1527 – ident: 10.1016/j.neunet.2018.07.006_b47 doi: 10.1109/IJCNN.2018.8489075 – year: 2015 ident: 10.1016/j.neunet.2018.07.006_b4 article-title: Data-efficient learning of feedback policies from image pixels using deep dynamical models – start-page: 465 year: 2011 ident: 10.1016/j.neunet.2018.07.006_b17 article-title: PILCO: A model-based and data-efficient approach to policy search – ident: 10.1016/j.neunet.2018.07.006_b73 – ident: 10.1016/j.neunet.2018.07.006_b41 – volume: 11 start-page: 3371 issue: Dec year: 2010 ident: 10.1016/j.neunet.2018.07.006_b67 article-title: Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion publication-title: Journal of Machine Learning Research (JMLR) – volume: 184 start-page: 232 issue: C year: 2016 ident: 10.1016/j.neunet.2018.07.006_b70 article-title: Auto-encoder based dimensionality reduction publication-title: Neurocomput doi: 10.1016/j.neucom.2015.08.104 – ident: 10.1016/j.neunet.2018.07.006_b38 – ident: 10.1016/j.neunet.2018.07.006_b45 – year: 2018 ident: 10.1016/j.neunet.2018.07.006_b75 article-title: Decoupling dynamics and reward for transfer learning – ident: 10.1016/j.neunet.2018.07.006_b2 – ident: 10.1016/j.neunet.2018.07.006_b59 – ident: 10.1016/j.neunet.2018.07.006_b20 – start-page: 1 year: 2015 ident: 10.1016/j.neunet.2018.07.006_b10 article-title: Autonomous Learning of State Representations for Control: An Emerging Field Aims to Autonomously Learn State Representations for Reinforcement Learning Agents from Their Real-World Sensor Observations publication-title: KI - Küstliche Intelligenz – start-page: 2172 year: 2016 ident: 10.1016/j.neunet.2018.07.006_b12 article-title: Infogan: Interpretable representation learning by information maximizing generative adversarial nets |
| SSID | ssj0006843 |
| Score | 2.6570876 |
| SecondaryResourceType | review_article |
| Snippet | Representation learning algorithms are designed to learn abstract features that characterize data. State representation learning (SRL) focuses on a particular... |
| SourceID | hal proquest pubmed crossref elsevier |
| SourceType | Open Access Repository Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 379 |
| SubjectTerms | Algorithms Computer Science Disentanglement of control factors Humans Learning disentangled representations Low dimensional embedding learning Machine Learning - trends Reinforcement (Psychology) Reinforcement learning Robotics Robotics - methods Robotics - trends State representation learning |
| Title | State representation learning for control: An overview |
| URI | https://dx.doi.org/10.1016/j.neunet.2018.07.006 https://www.ncbi.nlm.nih.gov/pubmed/30268059 https://www.proquest.com/docview/2114699632 https://hal.science/hal-01858558 |
| Volume | 108 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDLbYduHC-zEeU0Bcy9YmTVNu08Q0nheYtFvUpikMoYJg48hvx27TSUggJI6NkrZyHPuz8tkGOJGJDbIklF6uBAUovvKUzYynktyqXpznwqd855tbORqLy0k4WYJBnQtDtEpn-yubXlprN9J10uy-Tqfdux66WomAx6cSVqhLDWgFPJZhE1r9i6vR7cIgS1WR53C-RwvqDLqS5lXYeWGJVOmrsoontT762UM1Hokq-RsOLf3RcA1WHJBk_epf12HJFhuwWjdpYO7MboIs4SQri1fWiUYFc80iHhhiVubo6mesXzBidNJtwRaMh-f3g5HnmiV4RshghkZLchvw0KSxkhkGGqlR3ES5b4zJ0QEh7olzLoxvTaq4TISNDbp3RGBZmEaB4NvQLF4Kuwss4knIjSJCiRVRJuKEW5728lhECG8C3gZeC0gbV0mcGlo865oy9qQrsWoSq-7RFbdsg7dY9VpV0vhjflTLXn_TCI3G_o-Vx7hVi49QAe1R_1rTGE7C-ChUH34bjuqd1Hii6JokKezL_F0HlKiNYSAP2rBTbfHiXahpUiEi3fv3z-3DMj1VjJgDaM7e5vYQcc0s7UDj9NPvOO39Agms9X4 |
| linkProvider | Elsevier |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1LT8MwDLZ4HODC-zGeAXEtW5s0TblNCDRgcIFJu0VtmsIQ6ibYOPLbsdt0CAmExLV12shx7C_KZxvgRCY2yJJQerkSdEDxladsZjyV5Fa14jwXPuU7397JTk9c98P-DJzXuTBEq3S-v_Lppbd2T5pOm83RYNC8b2GolQh4fCphhbY0C_Mi5BHx-k4_vngeUlXUOZT2SLzOnytJXoWdFJYolb4qa3hS46Of49PsExElf0OhZTS6XIElByNZu5rpKszYYg2W6xYNzO3YdZAlmGRl6co6zahgrlXEI0PEyhxZ_Yy1C0Z8Tror2IDe5cXDecdzrRI8I2QwRpcluQ14aNJYyQyPGalR3ES5b4zJMfwg6olzLoxvTaq4TISNDQZ3xF9ZmEaB4JswVwwLuw0s4knIjSI6iRVRJuKEW5628lhECG4C3gBeK0gbV0ec2lm86Jow9qwrtWpSq27RBbdsgDcdNarqaPwhH9W619_sQaOr_2PkMS7V9CdUPrvT7mp6hkJ4OgrVu9-Ao3olNe4nuiRJCjucvOmA0rTxEMiDBmxVSzz9FtqZVIhHd_49uUNY6DzcdnX36u5mFxbpTcWN2YO58evE7iPCGacHpQV_Ahl59kk |
| openUrl | ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=State+representation+learning+for+control%3A+An+overview&rft.jtitle=Neural+networks&rft.au=Lesort%2C+Timoth%C3%A9e&rft.au=D%C3%ADaz-Rodr%C3%ADguez%2C+Natalia&rft.au=Goudou%2C+Jean-Frano%CC%A7is&rft.au=Filliat%2C+David&rft.date=2018-12-01&rft.pub=Elsevier+Ltd&rft.issn=0893-6080&rft.eissn=1879-2782&rft.volume=108&rft.spage=379&rft.epage=392&rft_id=info:doi/10.1016%2Fj.neunet.2018.07.006&rft.externalDocID=S0893608018302053 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0893-6080&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0893-6080&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0893-6080&client=summon |