Solving Robust MDPs through No-Regret Dynamics

arXiv:2305.19035v2 Announce Type: replace
Abstract: Reinforcement Learning is a powerful framework for training agents to navigate different situations, but it is susceptible to changes in environmental dynamics. However, solving Markov Decision Processes that are robust to changes is difficult due to nonconvexity and size of action or state spaces. While most works have analyzed this problem by taking different assumptions on the problem, a general and efficient theoretical analysis is still missing. However, we generate a simple framework for improving …

abstract action agents arxiv cs.lg decision dynamics environmental framework however markov processes reinforcement reinforcement learning replace robust spaces state through training type while