Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories.
Li-Cheng LanHuan ZhangCho-Jui HsiehPublished in: ICLR (2023)
Keyphrases
- multi agent
- multi agent systems
- learning agents
- reinforcement learning
- intelligent agents
- autonomous agents
- cooperative
- multiagent systems
- software agents
- action selection
- multiagent reinforcement learning
- dynamic environments
- single agent
- multiple agents
- agent architecture
- agent technology
- probability distribution
- mobile agents
- agent systems
- spatio temporal
- function approximation
- incomplete information
- complex environments
- coalition formation
- game theoretic
- complex domains
- learning agent
- decision making
- wireless sensor networks
- action space
- artificial agents