通信喪失下でのロバストなマルチエージェント協調のための価値認識予測
Value-Aware Prediction for Robust Multi-Agent Coordination Under Communication Loss
通信が途切れる環境で、エージェントが欠落した状態情報を予測する際に、価値関数に基づく重み付けを導入し、予測モデルの学習を政策の進化に結びつける手法を提案した。
詳しい要約
1. どんなもの?
2. 先行研究と比べてどこがすごい?
3. 技術・手法の肝は?
4. どうやって有効だと検証した?
5. 議論はある?
6. 次に読むべき論文は?
※ AIが要旨から生成した要約です。正確性は原文をご確認ください。
著者: Kemal Devrim Kafadar, Eren Özaltun, Mahmud Efnan Şanlı, Feyza Orak, Emirhan Gazi, Kubilay Kağan Kömürcü, Nazım Kemal Üre
分類: cs.MA, cs.LG, cs.RO
原文アブストラクト
Robust multi-agent coordination relies heavily on inter-agent communication, which is frequently disrupted by physical and environmental constraints in real-world deployments. To maintain operation during these intermittent communication failures, agents can employ internal prediction models to estimate missing shared state information. However, predictors trained with standard reconstruction objectives treat all transitions equally. In a Reinforcement Learning context, this forces the model to waste capacity learning stochastic exploration noise and the outdated dynamics of suboptimal policies. In this paper, we propose a value-aware extension of Multi-Agent Observation Sharing under Communication Dropout (MARO) to patch communication gaps; we refer to this method as Value-Aware MARO. By dynamically weighting the predictor's loss function using advantage estimates derived from the underlying actor-critic architecture, our objective explicitly couples the predictor's learning process to the policy's evolution. This formulation focuses the model's capacity on the intentional, high-return dynamics actively reinforced by the agents. We evaluate our framework on several tasks within the Multi-Agent Particle Environment under varying communication reliability levels. Experimental results demonstrate that our approach maintains performance under declining communication reliability, particularly below 40%. While our method performs comparably in tasks where the baseline already maintains high coordination, our value-aware weighting effectively prevents the performance collapse observed in the standard predictor during high-attrition scenarios. In these environments, our method achieves an average improvement in mean returns of more than 20% and reduces performance variance by a mean of 64.7% compared to the standard unweighted baseline.
関連論文
- 協調の戦略を意味的に忘却する:マルチエージェント強化学習における役割不変な慣習の除去マルチエージェント強化学習
- 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
