Self-Attention for Deep Reinforcement Learning.
Xiangxiang ShenChuanhuan YinXinwen HouPublished in: ICMAI (2019)
Keyphrases
- reinforcement learning
- function approximation
- autonomous mental development
- learning algorithm
- artificial intelligence
- reinforcement learning algorithms
- multiscale
- robotic control
- temporal difference
- action selection
- markov decision processes
- optimal control
- learning problems
- database
- least squares
- knowledge base
- information retrieval
- real time