協調型マルチエージェント強化学習のための適応的価値分解と貪欲限界貢献計算
Adaptive Value Decomposition with Greedy Marginal Contribution Computation for Cooperative Multi-Agent Reinforcement Learning
非単調な報酬を持つ協調タスクに対応するため、動的に変化するエージェント群の協調価値を学習する適応的価値分解と、そこから算出する貪欲限界貢献を個別のクレジットとする新しい明示的クレジット割り当て手法AVGMを提案した論文。
著者: Shanqi Liu, Yujing Hu, Runze Wu, Dong Xing, Yu Xiong, Changjie Fan, Kun Kuang, Yong Liu
分類: cs.RO, cs.AI, cs.MA
原文アブストラクト
Real-world cooperation often requires intensive coordination among agents simultaneously. This task has been extensively studied within the framework of cooperative multi-agent reinforcement learning (MARL), and value decomposition methods are among those cutting-edge solutions. However, traditional methods that learn the value function as a monotonic mixing of per-agent utilities cannot solve the tasks with non-monotonic returns. This hinders their application in generic scenarios. Recent methods tackle this problem from the perspective of implicit credit assignment by learning value functions with complete expressiveness or using additional structures to improve cooperation. However, they are either difficult to learn due to large joint action spaces or insufficient to capture the complicated interactions among agents which are essential to solving tasks with non-monotonic returns. To address these problems, we propose a novel explicit credit assignment method to address the non-monotonic problem. Our method, Adaptive Value decomposition with Greedy Marginal contribution (AVGM), is based on an adaptive value decomposition that learns the cooperative value of a group of dynamically changing agents. We first illustrate that the proposed value decomposition can consider the complicated interactions among agents and is feasible to learn in large-scale scenarios. Then, our method uses a greedy marginal contribution computed from the value decomposition as an individual credit to incentivize agents to learn the optimal cooperative policy. We further extend the module with an action encoder to guarantee the linear time complexity for computing the greedy marginal contribution. Experimental results demonstrate that our method achieves significant performance improvements in several non-monotonic domains.
関連論文
- GARDEN: 証拠ナビゲーションによる汎用自律報酬設計マルチエージェント強化学習
- サポート保持蒸留によるマルチエージェント協調マルチエージェント強化学習
- 未来の協力者と協調する:参加タイミングがずれるマルチエージェント強化学習マルチエージェント強化学習
- 部分的観測動的ゲームにおける未知の対戦相手に対するレベルK政策の編成マルチエージェント強化学習
- 置換ロバスト性だけでは不十分:マルチエージェントTransformer方策における行動崩壊マルチエージェント強化学習
- テスト時マルチエージェント協調のための分解価値勾配フローマルチエージェント強化学習
