動画検索
関連広告
検索結果
Outline of the Talk
Reinforcement Learning via Policy Optimization
The Power of Ho-Norm Constraint
Linear Systems with State Feedback
Mixed H2/H Control Synthesis
Connection to Other Models
Implicit Regularization: Proof Highlights
Simulations
Implication for Multi-Agent RL: Zero-Sum LQ Games
Benefit from Game Formulation: Model-free H₂/Ho Control Design