conftrace_

multi-agent policy gradient

5 papers

Explore in graph

Also known as

MAPG

Co-occurring keywords · papers mentioning both

credit assignment (2) policy gradient (2) multi-agent reinforcement learning (2) relative overgeneralization (1) multi-agent system (1) actor-critic framework (1) agent topology (1) baseline function (1) centralized-decentralized mismatch (1) coalition utility (1)

Papers

Optimistic Multi-Agent Policy Gradient ICML 2024 TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient AAAI 2024 Difference Advantage Estimation for Multi-Agent Policy Gradients ICML 2022 DOP: Off-Policy Multi-Agent Decomposed Policy Gradients ICLR 2021 Settling the Variance of Multi-Agent Policy Gradients NeurIPS 2021