Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2024
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866916235449466880 |
|---|---|
| author | Fei, Yingjie Xu, Ruitu |
| author_facet | Fei, Yingjie Xu, Ruitu |
| contents | We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from existing literature as a performance metric could induce policies with equilibrium bias that favor the most risk-sensitive agents and overlook the other agents. To address such deficiency of the naive regret, we propose a novel notion of regret, which we call risk-balanced regret, and show through a lower bound that it overcomes the issue of equilibrium bias. Furthermore, we develop a self-play algorithm for learning Nash, correlated, and coarse correlated equilibria in risk-sensitive Markov games. We prove that the proposed algorithm attains near-optimal regret guarantees with respect to the risk-balanced regret. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_02724 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning Fei, Yingjie Xu, Ruitu Machine Learning Computer Science and Game Theory We study risk-sensitive multi-agent reinforcement learning under general-sum Markov games, where agents optimize the entropic risk measure of rewards with possibly diverse risk preferences. We show that using the regret naively adapted from existing literature as a performance metric could induce policies with equilibrium bias that favor the most risk-sensitive agents and overlook the other agents. To address such deficiency of the naive regret, we propose a novel notion of regret, which we call risk-balanced regret, and show through a lower bound that it overcomes the issue of equilibrium bias. Furthermore, we develop a self-play algorithm for learning Nash, correlated, and coarse correlated equilibria in risk-sensitive Markov games. We prove that the proposed algorithm attains near-optimal regret guarantees with respect to the risk-balanced regret. |
| title | Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning |
| topic | Machine Learning Computer Science and Game Theory |
| url | https://arxiv.org/abs/2405.02724 |