Robust Domain Randomised Reinforcement Learning through Peer-to-Peer Distillation
This paper offers an incremental improvement for researchers and practitioners using domain randomisation in reinforcement learning to achieve more stable and robust policy learning.
This paper addresses the instability of domain randomisation in reinforcement learning by introducing P2PDRL, a peer-to-peer online distillation strategy. P2PDRL enables robust learning across a wider randomisation distribution and more robust generalisation to new environments in continuous control tasks.
In reinforcement learning, domain randomisation is an increasingly popular technique for learning more general policies that are robust to domain-shifts at deployment. However, naively aggregating information from randomised domains may lead to high variance in gradient estimation and unstable learning process. To address this issue, we present a peer-to-peer online distillation strategy for RL termed P2PDRL, where multiple workers are each assigned to a different environment, and exchange knowledge through mutual regularisation based on Kullback-Leibler divergence. Our experiments on continuous control tasks show that P2PDRL enables robust learning across a wider randomisation distribution than baselines, and more robust generalisation to new environments at testing.