Recurrent Reinforcement Learning: A Hybrid Approach.
Xiujun LiLihong LiJianfeng GaoXiaodong HeJianshu ChenLi DengJi HePublished in: CoRR (2015)
Keyphrases
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- state space
- markov decision processes
- optimal policy
- temporal difference learning
- robotic control
- model free
- feed forward
- learning process
- action selection
- supervised learning
- autonomous learning
- multi agent
- artificial neural networks
- evolutionary learning
- learning problems
- website
- transition model
- learning algorithm
- machine learning
- multi unit combinatorial auctions
- reinforcement learning methods
- back propagation
- optimal control
- data sets
- dynamic programming
- support vector
- decision trees
- search engine
- data mining
- neural network