Batch Reinforcement Learning Through Continuation Method.
Yijie GuoShengyu FengNicolas Le RouxEd ChiHonglak LeeMinmin ChenPublished in: ICLR (2021)
Keyphrases
- synthetic data
- similarity measure
- dynamic programming
- theoretical analysis
- detection method
- reinforcement learning
- decision trees
- high precision
- prior knowledge
- cost function
- probabilistic model
- classification method
- temporal difference
- optimization method
- segmentation method
- optimization algorithm
- support vector machine svm
- computationally efficient
- multiresolution
- artificial neural networks
- computational complexity