Actor-critic reinforcement learning for tracking control in robotics.
Yudha P. PaneSubramanya P. NageshraoRobert BabuskaPublished in: CDC (2016)
Keyphrases
- actor critic
- tracking control
- reinforcement learning
- optimal control
- control law
- nonlinear systems
- policy gradient
- temporal difference
- reinforcement learning algorithms
- neuro fuzzy
- approximate dynamic programming
- function approximation
- adaptive control
- policy iteration
- adaptive neural
- gradient method
- state space
- artificial intelligence
- model free
- fuzzy model
- markov decision processes
- optimal policy
- dynamic programming
- average reward
- fuzzy controller
- closed loop
- rl algorithms
- fuzzy systems
- machine learning
- action selection
- control policy
- inverted pendulum
- kalman filter
- dynamical systems