Reinforcement learning autonomously identifying the source of errors for agents in a group mission.
Keishu UtimulaKen-taro HayaschiKousuke NakanoKenta HongoRyo MaezonoPublished in: CoRR (2021)
Keyphrases
- reinforcement learning
- multi agent
- multi agent systems
- learning agents
- multiagent systems
- action selection
- agent receives
- cooperative
- group members
- multi agent environments
- robocup soccer
- autonomous agents
- multiple agents
- multiagent learning
- intelligent agents
- single agent
- multi agent reinforcement learning
- software agents
- initially unknown
- learning capabilities
- reinforcement learning agents
- artificial agents
- function approximation
- learning agent
- agent systems
- multiagent reinforcement learning
- fully autonomous
- agent model
- coalition formation
- agent technology
- agent architecture
- resource allocation
- optimal policy
- state space
- joint action
- complex environments
- partial observability
- evolutionary learning
- learning algorithm
- reinforcement learning algorithms
- temporal difference
- team members
- dynamic environments
- mobile agents