Actor-Critic Reinforcement Learning with Simultaneous Human Control and Feedback.
Kory W. MathewsonPatrick M. PilarskiPublished in: CoRR (2017)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- control problems
- policy gradient
- temporal difference
- function approximation
- reinforcement learning algorithms
- approximate dynamic programming
- control strategies
- gradient method
- policy iteration
- adaptive control
- neuro fuzzy
- control strategy
- control policy
- state space
- model free
- action selection
- policy gradient methods
- neural network
- control method
- markov decision processes
- transfer learning
- control system
- learning algorithm
- temporal difference learning
- supervised learning
- dynamic programming