A generic architecture for adaptive agents based on reinforcement learning.
Philippe PreuxSamuel DelepoulleJean-Claude DarchevillePublished in: Inf. Sci. (2004)
Keyphrases
- reinforcement learning
- multi agent
- adaptive behavior
- learning capabilities
- multi agent systems
- learning agents
- action selection
- multi agent reinforcement learning
- autonomous agents
- software agents
- learning algorithm
- cooperative
- multiagent systems
- agent receives
- function approximation
- reinforcement learning agents
- multiagent reinforcement learning
- multi agent environments
- artificial agents
- learned knowledge
- learning agent
- decision making
- multiple agents
- dynamic programming
- resource allocation
- agent systems
- robocup soccer
- single agent
- incomplete information
- social welfare
- dynamic environments
- transfer learning
- multiagent learning
- agent behavior
- agent architecture
- agent interactions
- agent model
- optimal control
- interacting agents
- mobile agents
- state space
- model free