Unsupervised Discovery of Transitional Skills for Deep Reinforcement Learning.
Qiangxing TianJinxin LiuGuanchu WangDonglin WangPublished in: IJCNN (2021)
Keyphrases
- reinforcement learning
- function approximation
- state space
- reinforcement learning algorithms
- learning algorithm
- model free
- markov decision processes
- skill development
- temporal difference
- optimal control
- dynamic programming
- active learning
- multi agent
- machine learning
- transfer learning
- optimal policy
- information technology
- reward function
- partially observable
- robot control
- temporal difference learning
- reinforcement learning methods
- entry level
- data sets