深層潜在空間競争：潜在空間における視覚制御ポリシーの競争学習
Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space
学習した世界モデルの潜在空間内で自己対戦を想像し、画像入力から競争的な視覚制御ポリシーを強化学習する手法を提案し、マルチエージェントレースベンチマークで有効性を示した。
著者: Wilko Schwarting, Tim Seyde, Igor Gilitschenski, Lucas Liebenwein, Ryan Sander, Sertac Karaman, Daniela Rus
分類: cs.LG, cs.AI, cs.RO
原文アブストラクト
Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competition (DLC), a novel reinforcement learning algorithm that learns competitive visual control policies through self-play in imagination. The DLC agent imagines multi-agent interaction sequences in the compact latent space of a learned world model that combines a joint transition function with opponent viewpoint prediction. Imagined self-play reduces costly sample generation in the real world, while the latent representation enables planning to scale gracefully with observation dimensionality. We demonstrate the effectiveness of our algorithm in learning competitive behaviors on a novel multi-agent racing benchmark that requires planning from image observations. Code and videos available at https://sites.google.com/view/deep-latent-competition.
関連論文
- 3Dマルチエンティティ物理環境における部分同変強化学習強化学習/マルチエージェント
