Recently regular decision processes have been pro- posed 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.
2021, Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI 2021, Pages -
Efficient PAC Reinforcement Learning in Regular Decision Processes (04b Atto di convegno in volume)
Ronca Alessandro, De Giacomo Giuseppe
Gruppo di ricerca: Artificial Intelligence and Knowledge Representation