ICLR 2021poster76 citations
Reinforcement Learning with Random Delays
Yann Bouteiller, Simon Ramstedt, Giovanni Beltrame, Christopher Pal, Jonathan Binas
Abstract
Action and observation delays commonly occur in many Reinforcement Learning applications, such as remote control scenarios. We study the anatomy of randomly delayed environments, and show that partially resampling trajectory fragments in hindsight allows for off-policy multi-step value estimation. We apply this principle to derive Delay-Correcting Actor-Critic (DCAC), an algorithm based on Soft Actor-Critic with significantly better performance in environments with delays. This is shown theoretically and also demonstrated practically on a delay-augmented version of the MuJoCo continuous control benchmark.
Reinforcement LearningDeep Reinforcement Learning
BibTeX
@inproceedings{
bouteiller2021reinforcement,
title={Reinforcement Learning with Random Delays},
author={Yann Bouteiller and Simon Ramstedt and Giovanni Beltrame and Christopher Pal and Jonathan Binas},
booktitle={International Conference on Learning Representations},
year={2021},
url={https://openreview.net/forum?id=QFYnKlBJYR}
}