Generating Teammates For Training Robust Ad Hoc Teamwork Agents Via Best-response Diversity

Abstract

Ad hoc teamwork (AHT) is the challenge of designing a robust learner agent that effectively collaborates with unknown teammates without prior coordination mechanisms. Early approaches address the AHT challenge by training the learner with a diverse set of handcrafted teammate policies, usually designed based on an expert's domain knowledge about the policies the learner may encounter. However, implementing teammate policies for training based on domain knowledge is not always feasible. In such cases, recent approaches attempted to improve the robustness of the learner by training it with teammate policies generated by optimising information-theoretic diversity metrics. The problem with optimising existing information-theoretic diversity metrics for teammate policy generation is the emergence of superficially different teammates. When used for AHT training, superficially different teammate behaviours may not improve a learner's robustness during collaboration with unknown teammates. In

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keyrahman2022generating

Related papers

• N-agent Ad Hoc Teamwork (2024)0.00
• Padiff: Predictive And Adaptive Diffusion Policies For Ad Hoc Teamwork (2025)0.00
• Learning To Coordinate With Anyone (2023)0.00
• A General Learning Framework For Open Ad Hoc Teamwork Using Graph-based Policy Learning (2022)0.00
• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16
• Collaborating With Humans Without Human Data (2021)0.00
• Adaptive Agent Architecture For Real-time Human-agent Teaming (2021)0.00
• The Impact Of Behavioral Diversity In Multi-agent Reinforcement Learning (2024)0.00