A General Learning Framework For Open Ad Hoc Teamwork Using Graph-based Policy Learning

Abstract

Open ad hoc teamwork is the problem of training a single agent to efficiently collaborate with an unknown group of teammates whose composition may change over time. A variable team composition creates challenges for the agent, such as the requirement to adapt to new team dynamics and dealing with changing state vector sizes. These challenges are aggravated in real-world applications in which the controlled agent only has a partial view of the environment. In this work, we develop a class of solutions for open ad hoc teamwork under full and partial observability. We start by developing a solution for the fully observable case that leverages graph neural network architectures to obtain an optimal policy based on reinforcement learning. We then extend this solution to partially observable scenarios by proposing different methodologies that maintain belief estimates over the latent environment states and team composition. These belief estimates are combined with our solution for the fully

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrahman2022a

Related papers

• Open Ad Hoc Teamwork With Cooperative Game Theory (2024)1.40
• N-agent Ad Hoc Teamwork (2024)0.00
• Making Friends In The Dark: Ad Hoc Teamwork Under Partial Observability (2023)5.84
• Generating Teammates For Training Robust Ad Hoc Teamwork Agents Via Best-response Diversity (2022)0.00
• Zero-shot Coordination In Ad Hoc Teams With Generalized Policy Improvement And Difference Rewards (2025)0.00
• Learning To Coordinate With Anyone (2023)0.00
• Assisting Unknown Teammates In Unknown Tasks: Ad Hoc Teamwork Under Partial Observability (2022)0.00
• GCS: Graph-based Coordination Strategy For Multi-agent Reinforcement Learning (2022)0.00