Efficient PAC Reinforcement Learning in Regular Decision Processes

Efficient PAC Reinforcement Learning in Regular Decision Processes

Alessandro Ronca, Giuseppe De Giacomo

Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence
Main Track. Pages 2026-2032. https://doi.org/10.24963/ijcai.2021/279

Recently regular decision processes have been proposed as a well-behaved form of non-Markov decision process. Regular decision processes are characterised by a transition function and a reward function that depend on the whole history, though regularly (as in regular languages). In practice both the transition and the reward functions can be seen as finite transducers. We study reinforcement learning in regular decision processes. Our main contribution is to show that a near-optimal policy can be PAC-learned in polynomial time in a set of parameters that describe the underlying decision process. We argue that the identified set of parameters is minimal and it reasonably captures the difficulty of a regular decision process.
Keywords:
Knowledge Representation and Reasoning: Action, Change and Causality
Machine Learning: Reinforcement Learning
Planning and Scheduling: Markov Decisions Processes