マルチエージェント探索のための反事実的条件付き尤度報酬
Counterfactual Conditional Likelihood Rewards for Multiagent Exploration
各エージェントの探索貢献をチーム全体の探索に対する独自の寄与として評価する反事実的条件付き尤度報酬を提案し、疎な報酬の協調タスクでの学習を加速させる。
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: Ayhan Alp Aydeniz, Robert Loftin, Kagan Tumer
分類: cs.MA, cs.RO
原文アブストラクト
Efficient exploration is critical for multiagent systems to discover coordinated strategies, particularly in open-ended domains such as search and rescue or planetary surveying. However, when exploration is encouraged only at the individual agent level, it often leads to redundancy, as agents act without awareness of how their teammates are exploring. In this work, we introduce Counterfactual Conditional Likelihood (CCL) rewards, which score each agent's exploration by isolating its unique contribution to team exploration. Unlike prior methods that reward agents solely for the novelty of their individual observations, CCL emphasizes observations that are informative with respect to the joint exploration of the team. Experiments in continuous multiagent domains show that CCL rewards accelerate learning for domains with sparse team rewards, where most joint actions yield zero rewards, and are particularly effective in tasks that require tight coordination among agents.
