Non-local Self-attention Structure for Function Approximation in Deep Reinforcement Learning.
Zhixiang WangXi XiaoGuangwu HuYao YaoDianyan ZhangZhendong PengQing LiShutao XiaPublished in: ICASSP (2019)
Keyphrases
- function approximation
- reinforcement learning
- state action space
- function approximators
- temporal difference learning algorithms
- model free
- tile coding
- learning tasks
- radial basis function
- reinforcement learning algorithms
- temporal difference learning
- temporal difference
- mountain car
- artificial neural networks
- learning algorithm
- supervised learning
- transfer learning
- neural network
- state space
- recommender systems
- multi agent
- training data
- feature selection