Model-Free $μ$ Synthesis via Adversarial Reinforcement Learning.
Darioush KeivanAaron HavensPeter SeilerGeir E. DullerudBin HuPublished in: CoRR (2021)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- multi agent
- temporal difference
- policy iteration
- state space
- rl algorithms
- learning algorithm
- markov decision processes
- supervised learning
- reinforcement learning methods
- policy evaluation
- transfer learning
- pattern recognition
- e learning
- average reward
- machine learning
- impedance control