Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks.
Takayuki OsaTatsuya HaradaPublished in: ICRA (2024)
Keyphrases
- multi agent
- cooperative
- reinforcement learning
- multi agent systems
- cooperative behavior
- optimal policy
- intelligent agents
- multiagent systems
- multi agent environments
- multiple agents
- agent based simulations
- multiagent reinforcement learning
- multi agent reinforcement learning
- learning agents
- single agent
- action selection
- autonomous agents
- agent behavior
- human computer interaction
- random sampling
- cooperative agents
- selective perception
- solve complex tasks
- model free
- transfer learning
- monte carlo
- sample size
- state space
- approximate policy iteration