Ramneet-Singh/foRmaL-notes

Research Notes on Reinforcement Learning from Formal Specifications.

Shell

foRmaL-notes

Research Notes on Reinforcement Learning from Formal Specifications.

Papers

A Framework for Transforming Specifications in Reinforcement Learning

Further Reading

Reactive Synthesis

Survey on Reactive Synthesis : Baier, C., de Alfaro, L., Forejt, V., Kwiatkowska, M.: Model checking probabilistic systems. In: Handbook of Model Checking, pp. 963–999. Springer (2018)

RL Algos for Discounted-Sum Rewards with Convergence and Efficient PAC Guarantees

Strehl, A.L., Li, L., Wiewiora, E., Langford, J., Littman, M.L.: PAC model- free reinforcement learning. In: Proceedings of the 23rd international conference on Machine learning. pp. 881–888 (2006)
Watkins, C.J., Dayan, P.: Q-learning. Machine learning 8(3-4), 279–292 (1992)

Specification-Aware Learning Algorithms

Icarte, R.T., Klassen, T.Q., Valenzano, R., McIlraith, S.A.: Reward machines: Exploiting reward function structure in reinforcement learning. arXiv preprint arXiv:2010.03950 (2020)
Jothimurugan, K., Bansal, S., Bastani, O., Alur, R.: Compositional reinforcement learning from logical specifications. In: Advances in Neural Information Processing Systems (2021)