AAAI 2025technical0 citations

Efficient Reinforcement Learning in Probabilistic Reward Machines

Xiaofeng Lin, Xuezhou Zhang

Abstract

In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret bound of Õ((HOAT)^(1/2) + H²O²A^(3/2) + H(T)^(1/2)), where H is the time horizon, O is the number of observations, A is the number of actions, and T is the number of time steps. This result improves over the best-known bound, Õ(H(OAT)^(1/2)), for MDPs with Deterministic Reward Machines (DRMs), a special case of PRMs. When T ≥ H³O³A² and OA ≥ H, our regret bound leads to a regret of Õ((HOAT)^(1/2)), which matches the established lower bound of Ω((HOAT)^(1/2)) for MDPs with DRMs up to a logarithmic factor. To the best of our knowledge, this is the first efficient algorithm for PRMs. Additionally, we present a new simulation lemma for non-Markovian rewards, which enables reward-free exploration for any non-Markovian reward given access to an approximate planner. Complementing our theoretical findings, we show through extensive experimental evaluations that our algorithm indeed outperforms prior methods in various PRM environments.

BibTeX
@article{Lin_Zhang_2025, title={Efficient Reinforcement Learning in Probabilistic Reward Machines}, volume={39}, url={https://ojs.aaai.org/index.php/AAAI/article/view/34061}, DOI={10.1609/aaai.v39i18.34061}, abstractNote={In this paper, we study reinforcement learning in Markov Decision Processes with Probabilistic Reward Machines (PRMs), a form of non-Markovian reward commonly found in robotics tasks. We design an algorithm for PRMs that achieves a regret bound of Õ((HOAT)^(1/2) + H²O²A^(3/2) + H(T)^(1/2)), where H is the time horizon, O is the number of observations, A is the number of actions, and T is the number of time steps. This result improves over the best-known bound, Õ(H(OAT)^(1/2)), for MDPs with Deterministic Reward Machines (DRMs), a special case of PRMs. When T ≥ H³O³A² and OA ≥ H, our regret bound leads to a regret of Õ((HOAT)^(1/2)), which matches the established lower bound of Ω((HOAT)^(1/2)) for MDPs with DRMs up to a logarithmic factor. To the best of our knowledge, this is the first efficient algorithm for PRMs. Additionally, we present a new simulation lemma for non-Markovian rewards, which enables reward-free exploration for any non-Markovian reward given access to an approximate planner.
Complementing our theoretical findings, we show through extensive experimental evaluations that our algorithm indeed outperforms prior methods in various PRM environments.}, number={18}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Lin, Xiaofeng and Zhang, Xuezhou}, year={2025}, month={Apr.}, pages={18728-18736} }
Efficient Reinforcement Learning in Probabilistic Reward Machines · AAAI 2025