Accelerating Policy Gradient by Estimating Value Function from Prior Computation in Deep Reinforcement Learning.
Md. Masudur RahmanYexiang XuePublished in: CoRR (2023)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- function approximation
- reinforcement learning algorithms
- optimal control
- policy search
- policy gradient methods
- gradient method
- model free reinforcement learning
- function approximators
- variance reduction
- state action
- state space
- neural network
- single agent
- control problems
- temporal difference
- model free
- machine learning