Off-Policy Fitted Q-Evaluation with Differentiable Function Approximators: Z-Estimation and Inference Theory

Mathematics

• Differentiable Function 100%
• Variance 66%
• Error Bound 33%
• Upper Bound 33%
• Minimax 33%
• Error Distribution 33%
• Estimation Theory 33%
• Confidence Interval 33%
• Statistical Analysis 33%
• Approximation Function 33%
• Statistical Theory 33%
• Tangent Space 33%
• Deep Neural Network 33%

Keyphrases

• Policy Estimation 16%