Robust Visual Domain Randomization for Reinforcement Learning

Autor:	Slaoui, Reda Bahi, Clements, William R., Foerster, Jakob N., Toth, Sébastien
Rok vydání:	2019
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence
Druh dokumentu:	Working Paper
Popis:	Producing agents that can generalize to a wide range of visually different environments is a significant challenge in reinforcement learning. One method for overcoming this issue is visual domain randomization, whereby at the start of each training episode some visual aspects of the environment are randomized so that the agent is exposed to many possible variations. However, domain randomization is highly inefficient and may lead to policies with high variance across domains. Instead, we propose a regularization method whereby the agent is only trained on one variation of the environment, and its learned state representations are regularized during training to be invariant across domains. We conduct experiments that demonstrate that our technique leads to more efficient and robust learning than standard domain randomization, while achieving equal generalization scores. Comment: Accepted at the BeTR-RL Workshop at ICLR 2020
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/1910.10537 Zobrazit plný text záznamu View this record from Arxiv