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

1 code implementation • 8 Feb 2024 • Hafez Ghaemi, Hamed Kebriaei, Alireza Ramezani Moghaddam, Majid Nili Ahamdabadi

Under a set of assumptions, we prove the convergence of the algorithm to a subjective notion of Markov perfect Nash equilibrium in NAMGs.

Multi-agent Reinforcement Learning