Get Started
Research questionHow can reinforcement-learning agents learn robust ad-hoc teamwork without pre-trained partners or hand-tuned partner generation?Agents trained with fixed or costly partner populations may struggle to generalize to unfamiliar teammates. Building diverse training partners can also require manual choices about how those partners are generated.
Multi-agent Systems
Reinforcement Learning
Latest papersRecent research connected to this question, newest first.Unsupervised Partner Design Enables Robust Ad-hoc TeamworkThe work addresses multi-agent reinforcement learning for ad-hoc teamwork in Level-Based Foraging, Overcooked-AI, and the Overcooked Generalisation Challenge, with additional evidence from a human-AI user study. It also considers joint partner-environment selection when a procedural level generator is available.research paper · Sep 1, 2026
Related questions
How can online reinforcement learning train multi-turn computer-use agents under partial observability, sparse rewards, and costly rollouts?How can LLM agents jointly adapt reasoning policies and hierarchical skill libraries during reinforcement learning?How can cooperative MARL detect meaningful environment or task changes online without redundant alarms?How can cooperative perception fuse independently trained detectors without pre-deployment coordination?
Home
Topics
Search
Library