Variance Reduced Domain Randomization for Reinforcement Learning With Policy Gradient.
Yuankun JiangChenglin LiWenrui DaiJunni ZouHongkai XiongPublished in: IEEE Trans. Pattern Anal. Mach. Intell. (2024)
Keyphrases
- policy gradient
- reinforcement learning
- actor critic
- variance reduction
- policy search
- reinforcement learning algorithms
- function approximation
- domain independent
- optimal control
- gradient method
- model free reinforcement learning
- transfer learning
- dynamic programming
- approximate dynamic programming
- learning algorithm
- reinforcement learning methods
- partially observable markov decision processes
- function approximators
- approximation methods
- average reward
- stochastic processes
- state action
- learning capabilities
- model free
- monte carlo
- markov chain
- state space
- search space
- policy gradient methods
- machine learning