Robustifying a Policy in Multi-Agent RL with Diverse Cooperative Behaviors and Adversarial Style Sampling for Assistive Tasks.
Takayuki OsaTatsuya HaradaPublished in: CoRR (2024)
Keyphrases
- multi agent
- cooperative
- reinforcement learning
- multi agent systems
- optimal policy
- cooperative behavior
- multiagent reinforcement learning
- multi agent environments
- single agent
- intelligent agents
- multi agent reinforcement learning
- agent based simulations
- human behavior
- reinforcement learning agents
- multiple agents
- multiagent systems
- autonomous agents
- solve complex tasks
- context aware
- cooperative agents
- policy evaluation
- policy gradient
- control policies
- game theory
- agent behavior
- average reward
- policy iteration
- markov decision process
- partially observable markov decision processes
- reinforcement learning algorithms
- policy search
- action selection
- human computer interaction
- random sampling
- function approximation
- selective perception
- transfer learning