Optimality of Reinforcement Learning Algorithms with Linear Function Approximation.
Ralf SchoknechtPublished in: NIPS (2002)
Keyphrases
- function approximation
- reinforcement learning algorithms
- reinforcement learning
- temporal difference learning algorithms
- function approximators
- temporal difference
- model free
- reinforcement learning problems
- temporal difference learning
- reinforcement learning methods
- radial basis function
- learning tasks
- state space
- td learning
- markov decision processes
- machine learning
- optimal solution
- policy search
- learning algorithm
- artificial neural networks
- average reward