Model-Free μ Synthesis via Adversarial Reinforcement Learning.
Darioush KeivanAaron HavensPeter SeilerGeir E. DullerudBin HuPublished in: ACC (2022)
Keyphrases
- model free
- reinforcement learning
- reinforcement learning algorithms
- function approximation
- temporal difference
- multi agent
- policy iteration
- state space
- rl algorithms
- average reward
- policy evaluation
- learning algorithm
- markov decision processes
- optimal policy
- machine learning
- learning problems
- least squares
- function approximators
- dynamic programming
- training data