Context-Specific Representation Abstraction for Deep Option Learning

• Published in: arXiv.org
• Main Authors: Abdulhai, Marwa, Dong-Ki, Kim, Riemer, Matthew, Liu, Miao, Tesauro, Gerald, How, Jonathan P
• Format: Paper
• Language: English
• Published: Ithaca Cornell University Library, arXiv.org 24.04.2022
• Subjects: Context; Learning; Recurrent neural networks; Representations

Hierarchical reinforcement learning has focused on discovering temporally extended actions, such as options, that can provide benefits in problems requiring extensive exploration. One promising approach that learns these options end-to-end is the option-critic (OC) framework. We examine and show in...