Improving Multi-Agent Cooperation using Theory of Mind
원문 초록
Recent advances in Artificial Intelligence have produced agents that can beat human world champions at games like Go, Starcraft, and Dota2. However, most of these models do not seem to play in a human-like manner: People infer others' intentions from their behaviour, and use these inferences in scheming and strategizing. Here, using a Bayesian Theory of Mind (ToM) approach, we investigated how much an explicit representation of others' intentions improves performance in a cooperative game. We compared the performance of humans playing with optimal-planning agents with and without ToM, in a cooperative game where players have to flexibly cooperate to achieve joint goals. We find that teams with ToM agents significantly outperform non-ToM agents when collaborating with all types of partners: non-ToM, ToM, as well as human players, and that the benefit of ToM increases the more ToM agents there are. These findings have implications for designing better cooperative agents.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
Transformer World Model for Sample Efficient Multi-Agent Reinforcement Learning
A Benchmark for Generalizing Across Diverse Team Strategies in Competitive Pokémon
AVA: Attentive VLM Agent for Mastering StarCraft II
Trajectory-Class-Aware Multi-Agent Reinforcement Learning
PMAT: Optimizing Action Generation Order in Multi-Agent Reinforcement Learning
Hierarchical Expert Prompt for Large-Language-Model: An Approach Defeat Elite AI in TextStarCraft II for the First Time
토론
이 논문과 연결된 포럼 글이 아직 없습니다.