On the Pitfalls of Learning to Cooperate with Self Play Agents Checkpointed to Capture Humans of Diverse Skill Levels.
Upasana BiswasLin GuanSubbarao KambhampatiPublished in: HRI (Companion) (2024)
Keyphrases
- cooperative
- learning algorithm
- learning process
- autonomous agents
- multi agent
- supervised learning
- skill levels
- multiagent learning
- learning systems
- knowledge acquisition
- online learning
- active learning
- prior knowledge
- reinforcement learning
- computer programming
- learning agents
- intelligent behavior
- game players
- real world