Oracle Complexity Reduction for Model-free LQR: A Stochastic Variance-Reduced Policy Gradient Approach.
Leonardo F. TosoHan WangJames AndersonPublished in: CoRR (2023)
Keyphrases
- model free
- complexity reduction
- policy gradient
- reinforcement learning algorithms
- reinforcement learning
- function approximation
- average reward
- optimal control
- reinforcement learning methods
- image coding
- variance reduction
- fractal image compression
- temporal difference
- monte carlo
- rl algorithms
- computational complexity
- policy iteration
- machine learning
- radial basis function
- optimal policy
- importance sampling
- stochastic games
- learning algorithm
- single agent
- dynamic programming