English

Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games

Machine Learning 2024-02-09 v1 Artificial Intelligence Multiagent Systems

Abstract

Classical multi-agent reinforcement learning (MARL) assumes risk neutrality and complete objectivity for agents. However, in settings where agents need to consider or model human economic or social preferences, a notion of risk must be incorporated into the RL optimization problem. This will be of greater importance in MARL where other human or non-human agents are involved, possibly with their own risk-sensitive policies. In this work, we consider risk-sensitive and non-cooperative MARL with cumulative prospect theory (CPT), a non-convex risk measure and a generalization of coherent measures of risk. CPT is capable of explaining loss aversion in humans and their tendency to overestimate/underestimate small/large probabilities. We propose a distributed sampling-based actor-critic (AC) algorithm with CPT risk for network aggregative Markov games (NAMGs), which we call Distributed Nested CPT-AC. Under a set of assumptions, we prove the convergence of the algorithm to a subjective notion of Markov perfect Nash equilibrium in NAMGs. The experimental results show that subjective CPT policies obtained by our algorithm can be different from the risk-neutral ones, and agents with a higher loss aversion are more inclined to socially isolate themselves in an NAMG.

Keywords

Cite

@article{arxiv.2402.05906,
  title  = {Risk-Sensitive Multi-Agent Reinforcement Learning in Network Aggregative Markov Games},
  author = {Hafez Ghaemi and Hamed Kebriaei and Alireza Ramezani Moghaddam and Majid Nili Ahamdabadi},
  journal= {arXiv preprint arXiv:2402.05906},
  year   = {2024}
}
R2 v1 2026-06-28T14:43:16.641Z