Using Reinforcement Learning to Coordinate Better.
Cora B. Excelente-ToledoNicholas R. JenningsPublished in: Comput. Intell. (2005)
Keyphrases
- reinforcement learning
- function approximation
- cooperative multi agent systems
- reinforcement learning algorithms
- robotic control
- optimal policy
- learning algorithm
- continuous state
- control problems
- markov decision processes
- state space
- dynamic programming
- learning process
- multi agent
- information systems
- machine learning
- supervised learning
- transfer learning
- mobile robot
- learning problems
- support vector
- action space
- learning agents
- evolutionary learning
- direct policy search