Provably Efficient Model-Free Constrained RL with Linear Function Approximation.
Arnob GhoshXingyu ZhouNess B. ShroffPublished in: NeurIPS (2022)
Keyphrases
- function approximation
- model free
- reinforcement learning
- temporal difference learning algorithms
- reinforcement learning algorithms
- temporal difference
- function approximators
- policy iteration
- temporal difference learning
- radial basis function
- td learning
- policy evaluation
- learning tasks
- rl algorithms
- state space
- reinforcement learning methods
- neural network
- support vector
- average reward
- machine learning
- genetic algorithm
- least squares
- learning process