Learning Minimax-Optimal Terminal State Estimators and Smoothers

Keyphrases

• Adversarial Disturbances 33%
• Attenuation 33%
• Complexity Guarantees 33%
• Corrupt 33%
• Discrete-time 33%
• Finite Sample 33%
• Free Policy 33%
• Linear Dynamical Systems 33%
• Maximum Size 33%
• Minimax 33%
• Minimax Estimator 33%
• Minimax Optimal 100%
• Model-free Algorithms 33%
• Numerical Experiments 33%
• Policy Gradient Method 66%
• Proposed Policy 33%
• Robustness Level 33%
• Sample Complexity 33%
• State Estimation 33%
• State Estimator 100%
• State Filtering 33%
• State Prediction 33%
• State Smoothing 33%
• Terminal State 100%

Computer Science

• discrete-time 33%
• Dynamical System 33%
• State Estimation 33%
• State Estimator 100%
• Terminal State 100%

Mathematics

• Discrete Time 33%
• Linear Dynamical Systems 33%
• Minimax 100%
• Minimax Estimation 33%
• Numerical Experiment 33%