Independent Skill Transfer for Deep Reinforcement Learning.
Qiangxing TianGuanchu WangJinxin LiuDonglin WangYachen KangPublished in: IJCAI (2020)
Keyphrases
- reinforcement learning
- transfer learning
- knowledge transfer
- learning algorithm
- function approximation
- reinforcement learning algorithms
- state space
- model free
- optimal control
- optimal policy
- supervised learning
- policy search
- previously learned
- markov decision processes
- neural network
- learning process
- multi agent
- training data
- case study
- artificial intelligence
- machine learning