Model-Free Optimal Control using SPSA with Complex Variables.
Long WangJingyi ZhuJames C. SpallPublished in: CISS (2021)
Keyphrases
- optimal control
- model free
- reinforcement learning
- risk sensitive
- policy iteration
- stochastic approximation
- control problems
- reinforcement learning algorithms
- rl algorithms
- dynamic programming
- feedback control
- control strategy
- infinite horizon
- impedance control
- temporal difference
- function approximation
- neural network
- policy evaluation
- partially observable markov decision processes
- support vector
- learning algorithm
- stochastic control
- machine learning