Accelerated Policy Gradient: On the Nesterov Momentum for Reinforcement Learning.
Yen-Ju ChenNai-Chieh HuangPing-Chun HsiehPublished in: CoRR (2023)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- function approximation
- policy search
- optimal control
- policy gradient methods
- semidefinite programming
- model free reinforcement learning
- learning algorithm
- single agent
- reinforcement learning methods
- state space
- average reward
- gradient method
- learning rate
- model free
- approximation methods
- temporal difference
- optimal policy
- function approximators
- state action
- neural network
- multi agent
- dynamic programming
- partially observable markov decision processes
- markov decision processes
- variance reduction
- markov decision process
- dynamical systems
- control strategy