Human-aligned reinforcement learning for autonomous agents and robots.
Francisco CruzThommen George KarimpanalMiguel A. SolisPablo BarrosRichard DazeleyPublished in: Neural Comput. Appl. (2023)
Keyphrases
- autonomous agents
- reinforcement learning
- multi agent
- dynamic environments
- multi agent environments
- multi agent systems
- human robot
- virtual humans
- incomplete information
- multiagent systems
- human robot interaction
- robot behavior
- robotic soccer
- learning agents
- changing environment
- resource bounded
- real robot
- complex environments
- intelligent behavior
- human users
- reward signal
- cooperative
- robotic systems
- distributed artificial intelligence
- coalition formation
- distributed control
- robot control
- mobile robot
- single agent
- reinforcement learning algorithms
- agent negotiation
- state space
- humanoid robot
- coordination mechanisms
- heterogeneous agents
- mental states
- learning algorithm
- agent behavior
- human subjects
- open systems
- function approximation