A Family of Robust Stochastic Operators for Reinforcement Learning.
Yingdong LuMark S. SquillanteChai Wah WuPublished in: NeurIPS (2019)
Keyphrases
- reinforcement learning
- direct policy search
- computationally efficient
- special case
- supervised learning
- monte carlo
- multi agent
- evolutionary algorithm
- dynamic programming
- neural network
- sufficient conditions
- learning algorithm
- machine learning
- optimal control
- parameter tuning
- reinforcement learning algorithms
- stochastic approximation
- data mining