Fast and Efficient Reinforcement Learning with Truncated Temporal Differences.
Pawel CichoszJan J. MulawkaPublished in: ICML (1995)
Keyphrases
- temporal difference
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- model free
- td learning
- evaluation function
- neural network
- step size
- monte carlo
- action selection
- artificial neural networks
- reinforcement learning methods
- policy evaluation
- machine learning
- markov decision processes
- differential evolution
- supervised learning
- state space
- pairwise