Reinforcement learning on explicitly specified time scales.
Ralf SchoknechtMartin A. RiedmillerPublished in: Neural Comput. Appl. (2003)
Keyphrases
- reinforcement learning
- function approximation
- multi agent
- state space
- reinforcement learning algorithms
- model free
- markov decision processes
- optimal policy
- policy search
- temporal difference
- supervised learning
- image structure
- dynamic programming
- learning process
- website
- learning algorithm
- learning capabilities
- multiple scales
- partially observable
- control problems
- markov decision process
- learning agents
- autonomous learning
- databases