AlphaSeq: Sequence Discovery With Deep Reinforcement Learning.
Yulin ShaoSoung Chang LiewTaotao WangPublished in: IEEE Trans. Neural Networks Learn. Syst. (2020)
Keyphrases
- optimal control
- reinforcement learning
- dynamic programming
- hidden state
- database
- function approximation
- real time
- knowledge discovery
- learning process
- optimal policy
- learning problems
- pattern discovery
- learning algorithm
- learning classifier systems
- reward function
- reinforcement learning algorithms
- temporal difference learning
- information retrieval