ConventionPlay: Capability-Limited Training for Robust Ad-Hoc Collaboration
Here we present ConventionPlay, an RL-based approach that teaches agents to discover their partner's optimal convention by training against a learned population of partners that exhibit different degrees of adaptability across conventions.
ProofPaper ↗
Key points
- Ad-hoc collaboration often requires agents to identify and adhere to some shared convention within a cooperative task.
- Existing work on reinforcement learning (RL) for ad-hoc collaboration focuses on training agents that adapt to the conventions established by their partners.
- Some of these partners follow a single, fixed convention, while others are able to adapt to a subset of the possible conventions for the task in question.
- The existence of partners that support a limited subset of conventions forces agents trained against this population to actively probe their partner's capabilities, and steer their partner towards the most effective joint strategy that they are capable of following.
Sources (1)
- [1]ConventionPlay: Capability-Limited Training for Robust Ad-Hoc CollaborationarXiv (AI, ML, NLP, CV, robotics, multi-agent) · Oct 8, 12:30 PM
Here we present ConventionPlay, an RL-based approach that teaches agents to discover their partner's optimal convention by training against a learned population of partners that exhibit different degrees of adaptability across conventions.
Ad-hoc collaboration often requires agents to identify and adhere to some shared convention within a cooperative task.
Extractive summary: sentences quoted from the sources.
