Model-free Safe Control for Zero-Violation Reinforcement Learning.
Weiye ZhaoTairan HeChangliu LiuPublished in: CoRL (2021)
Keyphrases
- model free
- reinforcement learning
- impedance control
- control problems
- reinforcement learning algorithms
- function approximation
- temporal difference
- policy iteration
- adaptive control
- control system
- policy evaluation
- state space
- control policy
- optimal control
- control strategies
- markov decision processes
- reinforcement learning methods
- control method
- action selection
- control strategy
- machine learning
- robot control
- optimal policy
- learning process
- multi agent
- decision trees
- learning algorithm