Variance-Reduced Deep Actor-Critic With an Optimally Subsampled Actor Recursion.
Lakshmi MandalRaghuram Bharadwaj DiddigiShalabh BhatnagarPublished in: IEEE Trans. Artif. Intell. (2024)
Keyphrases
- actor critic
- reinforcement learning
- policy gradient
- optimal control
- temporal difference
- neuro fuzzy
- approximate dynamic programming
- gradient method
- variance reduction
- reinforcement learning algorithms
- dynamic programming
- function approximation
- average reward
- multiresolution
- markov decision processes
- policy iteration