Research on Online Reinforcement Learning Method Based on Experience-Replay.
Ning HuZhijun GeXuanwen ChenChunguang DingHaobin ShiPublished in: ICIA (2018)
Keyphrases
- reinforcement learning
- experimental evaluation
- high precision
- objective function
- synthetic data
- similarity measure
- detection method
- preprocessing
- dynamic programming
- fully automatic
- clustering method
- optimization algorithm
- computationally efficient
- online learning
- real time
- computational cost
- prior knowledge
- theoretical analysis
- artificial neural networks
- computational complexity
- bayesian networks
- decision trees
- learning algorithm
- neural network