method · first seen 2 Nov 2026
decentralized actor-critic
Actor-critic reinforcement learning where each agent updates its policy using only local information and neighbor communication.
Mentions per week
PapersCodeDiscussion
Earliest sources
- Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy RemediesPapers · 2 Nov 2026 · Yizhou Zhang, Yashaswini Murthy, Laixi Shi, Adam Wierman
Latest sources
- Finite-Sample Convergence in Networked Average Reward MARL: Decentralization Pitfalls and Entropy RemediesPapers · 2 Nov 2026 · Yizhou Zhang, Yashaswini Murthy, Laixi Shi, Adam Wierman