Robotic Knee Tracking Control to Mimic the Intact Human Knee Profile Based on Actor-critic Reinforcement Learning.
Ruofan WuZhikai YaoJennie SiHe HuangPublished in: CoRR (2021)
Keyphrases
- actor critic
- reinforcement learning
- tracking control
- temporal difference
- optimal control
- policy gradient
- reinforcement learning algorithms
- function approximation
- approximate dynamic programming
- neuro fuzzy
- nonlinear systems
- policy iteration
- control law
- gradient method
- state space
- real time
- dynamic programming
- model free
- adaptive neural
- adaptive control
- closed loop
- monte carlo
- optimal policy
- rough sets
- genetic algorithm
- machine learning