Solver-Critic: A Reinforcement Learning Method for Discrete-Time-Constrained-Input Systems.
Xin YuanLu DongChangyin SunPublished in: IEEE Trans. Cybern. (2021)
Keyphrases
- dynamic programming
- pairwise
- high precision
- experimental evaluation
- reinforcement learning
- model free
- significant improvement
- computational cost
- high accuracy
- preprocessing
- input data
- clustering method
- detection method
- temporal difference
- machine learning
- synthetic data
- least squares
- cost function
- objective function
- similarity measure