Reinforcement Learning in Few-Shot Scenarios: A Survey.
Zhechao WangQiming FuJianping ChenYunzhe WangYou LuHongjie WuPublished in: J. Grid Comput. (2023)
Keyphrases
- reinforcement learning
- function approximation
- video sequences
- video data
- model free
- robotic control
- real world
- application scenarios
- learning algorithm
- video shots
- supervised learning
- state space
- markov decision processes
- real time
- dynamic programming
- hidden markov models
- optimal control
- multi agent
- e learning
- temporal difference
- machine learning
- temporal difference learning
- data sets