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

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

15 Oct 2019ICML 2020 1arXiv:1910.07072archive 2025-07-28

Chen-Yu Wei, Mehdi Jafarnia-Jahromi, Haipeng Luo, Hiteshi Sharma, Rahul Jain

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)), 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. (2019a) for ergodic MDPs in the infinite-horizon average-reward setting.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

bahh723/model-free-rl-algos mentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multi-Armed BanditsReinforcement LearningReinforcement Learning (RL)reinforcement-learning

Results from the paper archive 2025-07-28

No leaderboard rows for this paper in the archive.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections