|
[SK23]
Daqian Shao and Marta Kwiatkowska.
Sample Efficient Model-free Reinforcement Learning from LTL Specifications with Optimality Guarantees.
In Proc. 32nd International Joint Conference on Artificial Intelligence (IJCAI'23).
2023.
[Proposes new methods for LTL-based model-free reinforcement learning using LTL, using PRISM for policy evaluation.]
|
|
Links:
[Google]
[Google Scholar]
|