paper-with-me

Papers

Multi-Agent Trust Region Learning

2021-01-01 · Ying Wen, Hui Chen, Yaodong Yang, Zheng Tian, Minne Li, Xu Chen, Jun Wang

Trust-region methods are widely used in single-agent reinforcement learning. One advantage is that they guarantee a lower bound of monotonic payoff improvement for policy optimization at each iteration. Nonetheless, when applied in multi-agent settings, such guarantee is lost because an agent's payoff is also determined by other agents' adaptive behaviors. In fact, measuring agents' payoff improvements in multi-agent reinforcement learning (MARL) scenarios is still challenging. Although game-theoretical solution concepts such as Nash equilibrium can be applied, the algorithm (e.g., Nash-Q learning) suffers from poor scalability beyond two-player discrete games. To mitigate the above measurability and tractability issues, in this paper, we propose Multi-Agent Trust Region Learning (MATRL) method. MATRL augments the single-agent trust-region optimization process with the multi-agent solution concept of stable fixed point that is computed at the policy-space meta-game level. When multiple agents learn simultaneously, stable fixed points at the meta-game level can effectively measure agents' payoff improvements, and, importantly, a meta-game representation enjoys better scalability for multi-player games. We derive the lower bound of agents' payoff improvements for MATRL methods, and also prove the convergence of our method on the meta-game fixed points. We evaluate the MATRL method on both discrete and continuous multi-player general-sum games; results suggest that MATRL significantly outperforms strong MARL baselines on grid worlds, multi-agent MuJoCo, and Atari games.

📄 PDF Abstract BibTeX

Code (1)

matrl-project/matrl

Tasks

Atari GamesMuJoCoMulti-agent Reinforcement LearningQ-Learningreinforcement-learningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

A Game-Theoretic Approach to Multi-Agent Trust Region Optimization

2021-06-12 · Ying Wen, Hui Chen, Yaodong Yang, Zheng Tian 외

Trust region methods are widely applied in single-agent reinforcement learning problems due to their monotonic performance-improvement guarantee at every iteration. Nonetheless, when applied in multi-agent settings, the …

Atari GamesMuJoCoMulti-agent Reinforcement Learningreinforcement-learning+2

Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning

2021-09-23 · ICLR 2022 4 · Jakub Grudzien Kuba, Ruiqing Chen, Muning Wen, Ying Wen 외

Trust region methods rigorously enabled reinforcement learning (RL) agents to learn monotonically improving policies, leading to superior performance on a variety of tasks. Unfortunately, when it comes to multi-agent rei…

LEMMAMuJoCoMulti-agent Reinforcement Learningreinforcement-learning+2

Trust Region Bounds for Decentralized PPO Under Non-stationarity

2022-01-31 · Mingfei Sun, Sam Devlin, Jacob Beck, Katja Hofmann 외

We present trust region bounds for optimizing decentralized policies in cooperative Multi-Agent Reinforcement Learning (MARL), which holds even when the transition dynamics are non-stationary. This new analysis provides …

Multi-agent Reinforcement Learning

Rethinking Ratio-Based Trust Regions for Policy Optimization in Multi-Agent Reinforcement Learning

2026-05-09 · Chulabhaya Wijesundara, Andrea Baisero, Zhongheng Li, Gregory Castañón 외 arxiv

Centralized training with decentralized execution (CTDE) is a standard framework for cooperative multi-agent policy-gradient reinforcement learning, allowing agents to learn from joint information while acting from local…

Multi-agent Reinforcement Learning

Dealing with Non-Stationarity in MARL via Trust-Region Decomposition

2021-02-21 · ICLR 2022 4 · Wenhao Li, Xiangfeng Wang, Bo Jin, Junjie Sheng 외

Non-stationarity is one thorny issue in cooperative multi-agent reinforcement learning (MARL). One of the reasons is the policy changes of agents during the learning process. Some existing works have discussed various co…

Multi-agent Reinforcement Learning