Learning and Solving Regular Decision Processes
This work addresses a challenging, incremental problem in reinforcement learning for researchers focusing on non-Markovian decision-making.
The paper tackles the problem of learning Regular Decision Processes (RDPs) from data, which extend MDPs with non-Markovian dynamics, and demonstrates the feasibility of their approach by combining automata learning with history clustering and adapting MCTS.
Regular Decision Processes (RDPs) are a recently introduced model that extends MDPs with non-Markovian dynamics and rewards. The non-Markovian behavior is restricted to depend on regular properties of the history. These can be specified using regular expressions or formulas in linear dynamic logic over finite traces. Fully specified RDPs can be solved by compiling them into an appropriate MDP. Learning RDPs from data is a challenging problem that has yet to be addressed, on which we focus in this paper. Our approach rests on a new representation for RDPs using Mealy Machines that emit a distribution and an expected reward for each state-action pair. Building on this representation, we combine automata learning techniques with history clustering to learn such a Mealy machine and solve it by adapting MCTS to it. We empirically evaluate this approach, demonstrating its feasibility.