A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes
Keywords:Constraint Satisfaction And Optimization (CSO)
AbstractThis 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.
How to Cite
Wei, H., Liu, X., & Ying, L. (2022). A Provably-Efficient Model-Free Algorithm for Infinite-Horizon Average-Reward Constrained Markov Decision Processes. Proceedings of the AAAI Conference on Artificial Intelligence, 36(4), 3868-3876. https://doi.org/10.1609/aaai.v36i4.20302
AAAI Technical Track on Constraint Satisfaction and Optimization