Can Agents Run Relay Race with Strangers? Generalization of RL to Out-of-Distribution Trajectories.
Li-Cheng LanHuan ZhangCho-Jui HsiehPublished in: CoRR (2023)
Keyphrases
- multi agent
- learning agents
- reinforcement learning
- multi agent systems
- intelligent agents
- multiagent systems
- action selection
- cooperative
- multiple agents
- single agent
- autonomous agents
- dynamic environments
- software agents
- mobile agents
- multiagent reinforcement learning
- artificial agents
- probability distribution
- coalition formation
- optimal policy
- complex domains
- moving objects
- function approximation
- virtual communities
- agent model
- learning classifier systems
- decision theoretic
- decision making
- learning process
- learning agent
- markov decision processes
- multi agent reinforcement learning
- transfer learning