Greedy Multi-step Off-Policy Reinforcement Learning.
Yuhui WangPengcheng HeXiaoyang TanPublished in: CoRR (2021)
Keyphrases
- multi step
- reinforcement learning
- greedy algorithm
- dynamic programming
- lower bounding
- function approximation
- tumor classification
- single step
- k nearest neighbor
- search algorithm
- model free
- knn
- machine learning
- reinforcement learning algorithms
- td learning
- markov decision processes
- temporal difference
- feature selection
- text classification
- semi supervised
- action selection
- evolutionary algorithm