@article{Dohmen_Topper_Atia_Beckus_Trivedi_Velasquez_2022, title={Inferring Probabilistic Reward Machines from Non-Markovian Reward Signals for Reinforcement Learning}, volume={32}, url={https://ojs.aaai.org/index.php/ICAPS/article/view/19844}, DOI={10.1609/icaps.v32i1.19844}, abstractNote={The success of reinforcement learning in typical settings is predicated on Markovian assumptions on the reward signal by which an agent learns optimal policies. In recent years, the use of reward machines has relaxed this assumption by enabling a structured representation of non-Markovian rewards. In particular, such representations can be used to augment the state space of the underlying decision process, thereby facilitating non-Markovian reinforcement learning. However, these reward machines cannot capture the semantics of stochastic reward signals. In this paper, we make progress on this front by introducing probabilistic reward machines (PRMs) as a representation of non-Markovian stochastic rewards. We present an algorithm to learn PRMs from the underlying decision process and prove results around its correctness and convergence.}, number={1}, journal={Proceedings of the International Conference on Automated Planning and Scheduling}, author={Dohmen, Taylor and Topper, Noah and Atia, George and Beckus, Andre and Trivedi, Ashutosh and Velasquez, Alvaro}, year={2022}, month={Jun.}, pages={574-582} }