Cautiously Optimistic Policy Optimization and Exploration with Linear Function Approximation.
Andrea ZanetteChing-An ChengAlekh AgarwalPublished in: CoRR (2021)
Keyphrases
- function approximation
- function approximators
- temporal difference learning algorithms
- reinforcement learning
- exploration exploitation tradeoff
- action selection
- reinforcement learning problems
- model free
- radial basis function
- temporal difference
- temporal difference learning
- policy gradient
- learning tasks
- policy evaluation
- reinforcement learning algorithms
- temporal difference methods
- optimal policy
- policy search
- policy iteration
- actor critic
- markov decision problems
- learning experience
- active learning
- pattern recognition