Sample Complexity of Policy-Based Methods under Off-Policy Sampling and Linear Function Approximation.
Zaiwei ChenSiva Theja MaguluriPublished in: AISTATS (2022)
Keyphrases
- function approximation
- function approximators
- sample complexity
- radial basis function
- temporal difference learning algorithms
- reinforcement learning problems
- reinforcement learning
- temporal difference
- model selection
- cross validation
- neural network
- markov decision processes
- reinforcement learning algorithms
- model free
- learning problems
- learning experience
- collaborative filtering
- state space
- dynamic programming
- feature extraction
- machine learning