Generating and Adapting to Diverse Ad-Hoc Cooperation Agents in Hanabi
Hanabi is a cooperative game that brings the problem of modeling other players to the forefront. In this game, coordinated groups of players can leverage pre-established conventions to great effect, but playing in an ad-hoc setting requires agents to adapt to its partner's strategies with no previous coordination. Evaluating an agent in this setting requires a diverse population of potential partners, but so far, the behavioral diversity of agents has not been considered in a systematic way. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate diverse populations for this purpose, and generates a population of diverse Hanabi agents using MAP-Elites. We also postulate that agents can benefit from a diverse population during training and implement a simple "meta-strategy" for adapting to an agent's perceived behavioral niche. We show this meta-strategy can work better than generalist strategies even outside the population it was trained with if its partner's behavioral niche can be correctly inferred, but in practice a partner's behavior depends and interferes with the meta-agent's own behavior, suggesting an avenue for future research in characterizing another agent's behavior during gameplay.
Code (1)
Tasks
DiversitySimilar Papers 제목 키워드 기반
Diverse Agents for Ad-Hoc Cooperation in Hanabi
In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card g…
DiversityBehavioral Differences is the Key of Ad-hoc Team Cooperation in Multiplayer Games Hanabi
Ad-hoc team cooperation is the problem of cooperating with other players that have not been seen in the learning process. Recently, this problem has been considered in the context of Hanabi, which requires cooperation wi…
ClusteringReinforcement Learning (RL)Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners
Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-per…
Augmenting the action space with conventions to improve multi-agent cooperation in Hanabi
The card game Hanabi is considered a strong medium for the testing and development of multi-agent reinforcement learning (MARL) algorithms, due to its cooperative nature, partial observability, limited communication and …
Multi-agent Reinforcement LearningReinforcement Learning for Hanabi
Hanabi has become a popular game for research when it comes to reinforcement learning (RL) as it is one of the few cooperative card games where you have incomplete knowledge of the entire environment, thus presenting a c…
Card GamesDeep Reinforcement LearningQ-Learningreinforcement-learning+2