Deep Reinforcement Learning with Decorrelation.
Borislav MavrinHengshuai YaoLinglong KongPublished in: CoRR (2019)
Keyphrases
- reinforcement learning
- function approximation
- model free
- direct policy search
- state space
- policy search
- learning algorithm
- temporal difference learning
- deep learning
- reinforcement learning algorithms
- temporal difference
- transfer learning
- optimal policy
- machine learning
- neural network
- database
- blind source separation
- control problems
- robot control
- dynamic programming
- robotic control
- transition model
- search engine
- real time
- reward function
- action selection
- non stationary
- probabilistic model