Quantile-Based Deep Reinforcement Learning using Two-Timescale Policy Gradient Algorithms.
Jinyang JiangJiaqiao HuYijie PengPublished in: CoRR (2023)
Keyphrases
- reinforcement learning
- policy gradient
- learning algorithm
- gradient ascent
- natural gradient
- optimization problems
- policy gradient methods
- function approximation
- model free
- neural network
- computational complexity
- state space
- reinforcement learning algorithms
- reinforcement learning methods
- function approximators
- policy search