Optimistic Multi-Agent Policy Gradient
*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 matches the performance on the rest.
Code (1)
Tasks
MuJoCoQ-LearningMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Symmetric (Optimistic) Natural Policy Gradient for Multi-agent Learning with Parameter Convergence
Multi-agent interactions are increasingly important in the context of reinforcement learning, and the theoretical foundations of policy gradient methods have attracted surging research interest. We investigate the global…
Policy Gradient MethodsOptimistic Policy Gradient in Multi-Player Markov Games with a Single Controller: Convergence Beyond the Minty Property
Policy gradient methods enjoy strong practical performance in numerous tasks in reinforcement learning. Their theoretical understanding in multiagent settings, however, remains limited, especially beyond two-player compe…
Policy Gradient MethodsOptimistic Natural Policy Gradient: a Simple Efficient Policy Optimization Framework for Online RL
While policy optimization algorithms have played an important role in recent empirical success of Reinforcement Learning (RL), the existing theoretical understanding of policy optimization remains rather limited -- they …
Reinforcement Learning (RL)Sample-efficient actor-critic algorithms with an etiquette for zero-sum Markov games
We introduce algorithms based on natural policy gradient and two time-scale natural actor-critic, and analyze their sample complexity for solving two player zero-sum Markov games in the tabular case. Our results improve …
Policy Gradient MethodsOptimism as Risk-Seeking in Multi-Agent Reinforcement Learning
Risk sensitivity has become a central theme in reinforcement learning (RL), where convex risk measures and robust formulations provide principled ways to model preferences beyond expected return. Recent extensions to mul…
Multi-agent Reinforcement Learning