Efficient Deep Reinforcement Learning via Adaptive Policy Transfer.
Tianpei YangJianye HaoZhaopeng MengZongzhang ZhangYujing HuYingfeng ChenChangjie FanWeixun WangWulong LiuZhaodong WangJiajie PengPublished in: IJCAI (2020)
Keyphrases
- reinforcement learning
- optimal policy
- transfer learning
- data sets
- computationally expensive
- markov decision process
- partially observable
- knowledge transfer
- function approximation
- state and action spaces
- control problems
- least squares
- multi agent systems
- decision making
- learning algorithm
- machine learning
- neural network