Provably Efficient Model-Free Constrained RL with Linear Function Approximation.
Arnob GhoshXingyu ZhouNess B. ShroffPublished in: CoRR (2022)
Keyphrases
- function approximation
- model free
- reinforcement learning
- temporal difference learning algorithms
- reinforcement learning algorithms
- temporal difference
- function approximators
- temporal difference learning
- rl algorithms
- radial basis function
- policy evaluation
- learning tasks
- machine learning
- neural network
- policy iteration
- td learning
- state space
- feature vectors
- pattern recognition
- average reward
- reinforcement learning methods