Improving Multi-Agent Reinforcement Learning with Stable Prefix Policy

Abstract

Responsibility is one of the key notions in machine ethics and in the area of autonomous systems. It is a multi-faceted notion involving counterfactual reasoning about actions and strategies. In this paper, we study different variants of responsibility for LTLf outcomes based on strategic reasoning. We show a connection with notions in reactive synthesis, including the synthesis of winning, dominant, and best-effort strategies. This connection provides a strong computational grounding of responsibility, allowing us to characterize the worst-case computa- tional complexity and devise sound, complete, and optimal algorithms for anticipating and attributing responsibility.

Cite

Text

Deng et al. "Improving Multi-Agent Reinforcement Learning with Stable Prefix Policy." International Joint Conference on Artificial Intelligence, 2024. doi:10.24963/ijcai.2024/6

Markdown

[Deng et al. "Improving Multi-Agent Reinforcement Learning with Stable Prefix Policy." International Joint Conference on Artificial Intelligence, 2024.](https://mlanthology.org/ijcai/2024/deng2024ijcai-improving/) doi:10.24963/ijcai.2024/6

BibTeX

@inproceedings{deng2024ijcai-improving,
  title     = {{Improving Multi-Agent Reinforcement Learning with Stable Prefix Policy}},
  author    = {Deng, Yue and Wang, Zirui and Zhang, Yin},
  booktitle = {International Joint Conference on Artificial Intelligence},
  year      = {2024},
  pages     = {49-57},
  doi       = {10.24963/ijcai.2024/6},
  url       = {https://mlanthology.org/ijcai/2024/deng2024ijcai-improving/}
}