Metaoptimization on a Distributed System for Deep Reinforcement Learning

Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce instabilities, but the success of training remains str...

Full description

Saved in:
Bibliographic Details
Published inarXiv.org
Main Authors Heinrich, Greg, Frosio, Iuri
Format Paper
LanguageEnglish
Published Ithaca Cornell University Library, arXiv.org 07.02.2019
Subjects
Algorithms
Case depth
Computer networks
Intelligent agents
Machine learning
Parallel processing
State of the art
Training
Online AccessGet full text

Cover

More Information
Summary:Training intelligent agents through reinforcement learning is a notoriously unstable procedure. Massive parallelization on GPUs and distributed systems has been exploited to generate a large amount of training experiences and consequently reduce instabilities, but the success of training remains strongly influenced by the choice of the hyperparameters. To overcome this issue, we introduce HyperTrick, a new metaoptimization algorithm, and show its effective application to tune hyperparameters in the case of deep reinforcement learning, while learning to play different Atari games on a distributed system. Our analysis provides evidence of the interaction between the identification of the optimal hyperparameters and the learned policy, that is typical of the case of metaoptimization for deep reinforcement learning. When compared with state-of-the-art metaoptimization algorithms, HyperTrick is characterized by a simpler implementation and it allows learning similar policies, while making a more effective use of the computational resources in a distributed system.
ISSN:2331-8422