Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation.
Andrea ZanetteChing-An ChengAlekh AgarwalPublished in: COLT (2021)
Keyphrases
- function approximation
- function approximators
- temporal difference learning algorithms
- exploration exploitation tradeoff
- reinforcement learning
- reinforcement learning problems
- temporal difference
- temporal difference learning
- radial basis function
- model free
- policy gradient
- learning tasks
- action selection
- actor critic
- machine learning
- policy evaluation
- reinforcement learning algorithms
- policy search
- td learning
- markov decision problems
- artificial neural networks
- kernel function