Robots that are trained to perform a task in a fixed environment often fail when facing unexpected changes to the environment due to a lack of exploration. We propose a principled way to adapt the policy for better exploration in changing sparse-reward environments. Unlike previous works which explicitly model environmental changes, we analyze the relationship between the value function and the optimal exploration for a Gaussian-parameterized policy and show that our theory leads to an effective strategy for adjusting the variance of the policy, enabling fast adapt to changes in a variety of sparse-reward environments.
@article{arxiv.1903.06309,
title = {Adaptive Variance for Changing Sparse-Reward Environments},
author = {Xingyu Lin and Pengsheng Guo and Carlos Florensa and David Held},
journal= {arXiv preprint arXiv:1903.06309},
year = {2019}
}
Comments
Accepted as a conference at International Conference on Robotics and Automation(ICRA) 2019