Model-free Control of Chaos with Continuous Deep Q-learning.
Junya IkemotoToshimitsu UshioPublished in: CoRR (2019)
Keyphrases
- model free
- reinforcement learning
- impedance control
- function approximation
- reinforcement learning algorithms
- policy iteration
- control problems
- control system
- temporal difference
- control strategy
- optimal control
- control strategies
- rl algorithms
- chaotic systems
- radial basis function
- control method
- action space
- neural network
- markov decision processes
- learning experience
- machine learning