Model-Free Dual Heuristic Dynamic Programming.
Zhen NiHaibo HeXiangnan ZhongDanil V. ProkhorovPublished in: IEEE Trans. Neural Networks Learn. Syst. (2015)
Keyphrases
- model free
- dynamic programming
- reinforcement learning
- function approximation
- reinforcement learning algorithms
- policy iteration
- lagrangian relaxation
- temporal difference
- state space
- dynamic programming algorithms
- pattern recognition
- optimal policy
- optimal control
- infinite horizon
- single machine
- impedance control
- artificial neural networks
- policy evaluation
- action selection
- machine learning
- markov decision processes
- linear programming
- lower bound