A General Family of Robust Stochastic Operators for Reinforcement Learning.
Yingdong LuMark S. SquillanteChai Wah WuPublished in: CoRR (2018)
Keyphrases
- reinforcement learning
- special case
- direct policy search
- closely related
- stochastic approximation
- function approximation
- dynamic programming
- temporal difference
- state space
- database
- learning algorithm
- machine learning
- data sets
- multi agent systems
- multi agent
- case study
- optimal control
- stochastic optimization
- computationally tractable
- temporal difference learning
- neural network