Soft Actor-Critic Reinforcement Learning for robotic manipulator with Hindsight Experience Replay.
Tao YanWen-an ZhangSimon X. YangLi YuPublished in: Int. J. Robotics Autom. (2019)
Keyphrases
- actor critic
- reinforcement learning
- robotic manipulator
- temporal difference
- approximate dynamic programming
- policy gradient
- reinforcement learning algorithms
- optimal control
- function approximation
- policy iteration
- gradient method
- neuro fuzzy
- control scheme
- state space
- model free
- action selection
- visual servoing
- learning algorithm
- robotic systems
- average reward
- temporal difference learning
- degrees of freedom
- control system
- rl algorithms
- evaluation function
- multiple models
- markov decision processes
- finite state
- robot control
- adaptive control
- neural network
- dynamical systems
- monte carlo
- video sequences
- machine learning