NSF PAR Search | NSF Public Access Repository

Note: When clicking on a Digital Object Identifier (DOI) number, you will be taken to an external site maintained by the publisher. Some full text articles may not yet be available without a charge during the embargo (administrative interval).
What is a DOI Number?

Some links on this page may take you to non-federal websites. Their policies may differ from this site.

Model- free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes

Chen-Yu Wei, Mehdi Jafarnia (July 2021, Proceedings of Machine Learning Research)
null (Ed.)
Full Text Available
Learning Infinite-horizon Average-reward MDPs with Linear Function Approximation

Chen-Yu Wei, Mehdi Jafarnia (January 2020, Proceedings of Machine Learning Research)

Full Text Available
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes”, Proc. ICML 2020. (arXiv:1910.07072)

Chen-Yu Wei, Mehdi Jafarnia-Jahromi (January 2020, Proceedings of the 37th International Conference on Machine Learning)

Full Text Available
Model-free Reinforcement Learning in Infinite-horizon Average-reward Markov Decision Processes”, ICML (Int'l Conf. on Machine Learning) 2020.

Chen-Yu Wei, Mehdi Jafarnia-Jahromi (January 2020, Proceedings of Machine Learning Research)

Model-free reinforcement learning is known to be memory and computation efficient and more amendable to large scale problems. In this paper, two model-free algorithms are introduced for learning infinite-horizon average-reward Markov Decision Processes (MDPs). The first algorithm reduces the problem to the discounted-reward version and achieves O(𝑇^2/3) regret after 𝑇 steps, under the minimal assumption of weakly communicating MDPs. To our knowledge, this is the first model-free algorithm for general MDPs in this setting. The second algorithm makes use of recent advances in adaptive algorithms for adversarial multi-armed bandits and improves the regret to O(T^{1/2}), albeit with a stronger ergodic assumption. This result significantly improves over the O(T^{3/4}) regret achieved by the only existing model-free algorithm by Abbasi-Yadkori et al. (2019) for ergodic MDPs in the infinite-horizon average-reward setting.
more » « less
Full Text Available

Search for: All records