Reinforcement learning and neural reinforcement learning.
Samira SehadClaude F. TouzetPublished in: ESANN (1994)
Keyphrases
- reinforcement learning
- function approximation
- markov decision processes
- temporal difference learning
- machine learning
- fitted q iteration
- model free
- state space
- reinforcement learning algorithms
- learning process
- temporal difference
- learning algorithm
- data sets
- neural network
- function approximators
- dynamic programming
- supervised learning
- optimal control
- learning tasks
- partially observable
- markov decision process
- autonomous learning
- policy search
- least squares