Bridging Exploration and General Function Approximation in Reinforcement Learning: Provably Efficient Kernel and Neural Value Iterations.
Zhuoran YangChi JinZhaoran WangMengdi WangMichael I. JordanPublished in: CoRR (2020)
Keyphrases
- function approximation
- reinforcement learning
- temporal difference learning
- function approximators
- temporal difference
- temporal difference learning algorithms
- model free
- mountain car
- learning tasks
- neural network
- exploration exploitation tradeoff
- reinforcement learning algorithms
- optimal policy
- kernel function
- radial basis function
- learning problems
- data mining
- reinforcement learning problems
- td learning
- supervised learning
- multi agent