Optimistic Multi-agent Policy Gradient

Abstract

*Relative overgeneralization* (RO) occurs in cooperative multi-agent learning tasks when agents converge towards a suboptimal joint policy due to overfitting to suboptimal behavior of other agents. No methods have been proposed for addressing RO in multi-agent policy gradient (MAPG) methods although these methods produce state-of-the-art results. To address this gap, we propose a general, yet simple, framework to enable optimistic updates in MAPG methods that alleviate the RO problem. Our approach involves clipping the advantage to eliminate negative values, thereby facilitating optimistic updates in MAPG. The optimism prevents individual agents from quickly converging to a local optimum. Additionally, we provide a formal analysis to show that the proposed method retains optimality at a fixed point. In extensive evaluations on a diverse set of tasks including the *Multi-agent MuJoCo* and *Overcooked* benchmarks, our method outperforms strong baselines on 13 out of 19 tested tasks and m

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyzhao2023optimistic

Related papers

• Settling The Variance Of Multi-agent Policy Gradients (2021)0.00
• Asynchronous, Option-based Multi-agent Policy Gradient: A Conditional Reasoning Approach (2022)0.00
• Robust And Diverse Multi-agent Learning Via Rational Policy Gradient (2025)0.00
• Optimistic Natural Policy Gradient: A Simple Efficient Policy Optimization Framework For Online RL (2023)0.00
• TAPE: Leveraging Agent Topology For Cooperative Multi-agent Policy Gradient (2023)3.58
• Symmetric (optimistic) Natural Policy Gradient For Multi-agent Learning With Parameter Convergence (2022)0.00
• Optimistic Policy Gradient In Multi-player Markov Games With A Single Controller: Convergence Beyond The Minty Property (2023)3.58
• Learning Explicit Credit Assignment For Cooperative Multi-agent Reinforcement Learning Via Polarization Policy Gradient (2022)4.52