Provably Efficient Model-Free Algorithms for Non-stationary CMDPs

Honghao Wei, Arnob Ghosh, Ness B. Shroff, Lei Ying, Xingyu Zhou

Abstract: We study model-free reinforcement learning (RL) algorithms in episodic non-stationary constrained Markov decision processes (CMDPs), in which an agent aims to maximize the expected cumulative rewar...