# Taming Equilibrium Bias in Risk-Sensitive Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2405.02724 · HTML: https://mlsanity.com/paper/2405.02724/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 30 references that are in the map.
- First posted on arXiv 4 May 2024.

## Builds on (most cited first, 15 of 15)

- [Provable Self-Play Algorithms for Competitive Reinforcement Learning](https://mlsanity.com/paper/2002.04017/) (2020)
- [Near-Optimal Reinforcement Learning with Self-Play](https://mlsanity.com/paper/2006.12007/) (2020)
- [A Sharp Analysis of Model-based Reinforcement Learning with Self-Play](https://mlsanity.com/paper/2010.01604/) (2020)
- [Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium](https://mlsanity.com/paper/2002.07066/) (2020)
- [Model-Based Multi-Agent RL in Zero-Sum Markov Games with Near-Optimal Sample Complexity](https://mlsanity.com/paper/2007.07461/) (2020)
- [Risk-Sensitive Reinforcement Learning: Near-Optimal Risk-Sample Tradeoff in Regret](https://mlsanity.com/paper/2006.13827/) (2020)
- [Exponential Bellman Equation and Improved Regret Bounds for Risk-Sensitive Reinforcement Learning](https://mlsanity.com/paper/2111.03947/) (2021)
- [Learn to Match with No Regret: Reinforcement Learning in Markov Matching Markets](https://mlsanity.com/paper/2203.03684/) (2022)
- [Convergence and Alignment of Gradient Descent with Random Backpropagation Weights](https://mlsanity.com/paper/2106.06044/) (2021)
- [On the Landscape of Synchronization Networks: A Perspective from Nonconvex Optimization](https://mlsanity.com/paper/1809.11083/) (2018)
- [Meta Learning in the Continuous Time Limit](https://mlsanity.com/paper/2006.10921/) (2020)
- [Online Learning in Unknown Markov Games](https://mlsanity.com/paper/2010.15020/) (2020)
- [Finding Regularized Competitive Equilibria of Heterogeneous Agent Macroeconomic Models with Reinforcement Learning](https://mlsanity.com/paper/2303.04833/) (2023)
- [Zero-sum Risk-Sensitive Stochastic Games](https://mlsanity.com/paper/1604.01896/) (2016)
- [Cascaded Gaps: Towards Gap-Dependent Regret for Risk-Sensitive Reinforcement Learning](https://mlsanity.com/paper/2203.03110/) (2022)

## Abstract (arXiv)

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.