Deterministic policy gradient adaptive dynamic programming for model-free optimal control.
Yongwei ZhangBo ZhaoDerong LiuPublished in: Neurocomputing (2020)
Keyphrases
- optimal control
- model free
- policy gradient
- dynamic programming
- reinforcement learning
- actor critic
- reinforcement learning algorithms
- rl algorithms
- function approximation
- policy iteration
- impedance control
- infinite horizon
- control problems
- policy evaluation
- average reward
- temporal difference
- state space
- optimal policy
- reinforcement learning methods
- markov decision processes
- approximate dynamic programming
- adaptive control
- state action
- control strategy
- real time
- machine learning
- learning algorithm
- genetic algorithm
- function approximators
- neural network
- decision problems
- control law
- learning problems