Learning classifier system equivalent with reinforcement learning with function approximation.
Atsushi WadaKeiki TakadamaKatsunori ShimoharaPublished in: GECCO Workshops (2005)
Keyphrases
- function approximation
- learning classifier systems
- reinforcement learning
- relational reinforcement learning
- temporal difference
- model free
- temporal difference learning
- temporal difference learning algorithms
- function approximators
- reinforcement learning algorithms
- state space
- learning algorithm
- markov decision processes
- learning tasks
- transfer learning
- dynamic programming
- optimal policy
- supervised learning
- action selection
- evolutionary algorithm
- genetic algorithm
- neural network
- policy iteration
- learning process
- actor critic
- td learning
- machine learning