A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes

Honghao Wei; Xin Liu; Lei Ying

AAAI 2022technical32 citations

A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes

Abstract

This paper presents a model-free reinforcement learning (RL) algorithm for infinite-horizon average-reward Constrained Markov Decision Processes (CMDPs). Considering a learning horizon K, which is sufficiently large, the proposed algorithm achieves sublinear regret and zero constraint violation. The bounds depend on the number of states S, the number of actions A, and two constants which are independent of the learning horizon K.

BibTeX

@inproceedings{aaai2022_aprovablyefficie,
  title = {A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes},
  author = {Honghao Wei and Xin Liu and Lei Ying},
  booktitle = {AAAI 2022},
  year = {2022}
}