Adaptive Assist-as-needed Control Based on Actor-Critic Reinforcement Learning.
Yufeng ZhangShuai LiKaren J. NolanDamiano ZanottoPublished in: IROS (2019)
Keyphrases
- actor critic
- reinforcement learning
- optimal control
- control problems
- temporal difference
- policy gradient
- approximate dynamic programming
- adaptive control
- gradient method
- control strategy
- function approximation
- reinforcement learning algorithms
- control policy
- neuro fuzzy
- control method
- control system
- control strategies
- policy iteration
- natural actor critic
- dynamic programming
- model free
- markov decision processes
- rl algorithms
- supervised learning
- learning capabilities
- control scheme
- transfer learning
- average reward
- optimal policy
- state space
- learning algorithm