Parallel Reinforcement Learning with Linear Function Approximation.
Matthew Jon GroundsDaniel KudenkoPublished in: Adaptive Agents and Multi-Agents Systems (2007)
Keyphrases
- function approximation
- reinforcement learning
- function approximators
- temporal difference learning algorithms
- temporal difference
- mountain car
- temporal difference learning
- model free
- learning tasks
- state action space
- tile coding
- radial basis function
- reinforcement learning algorithms
- dynamic programming
- learning algorithm
- markov decision processes
- machine learning
- decision trees
- td learning
- transfer learning
- training data