Generating attentive goals for prioritized hindsight reinforcement learning.
Peng LiuChenjia BaiYingnan ZhaoChenyao BaiWei ZhaoXianglong TangPublished in: Knowl. Based Syst. (2020)
Keyphrases
- reinforcement learning
- action selection
- state space
- learning algorithm
- learning process
- function approximation
- reinforcement learning algorithms
- dynamic programming
- visual attention
- temporal difference
- neural network
- temporal difference learning
- robotic control
- policy search
- automatically generating
- possibilistic logic
- partially observable
- generation process
- model free
- vision system
- supervised learning
- hidden markov models