Applications of the self-organising map to reinforcement learning.
Andrew James SmithPublished in: Neural Networks (2002)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- markov decision processes
- learning algorithm
- state space
- model free
- machine learning
- dynamic programming
- temporal difference
- direct policy search
- databases
- temporal difference learning
- action selection
- learning classifier systems
- transfer learning
- monte carlo
- optimal policy
- supervised learning
- partially observable
- control problems
- robot control
- markov decision process
- search algorithm
- reinforcement learning methods
- autonomous learning
- robotic control
- multi agent