Minimax-optimal off-policy evaluation with linear function approximation

Mathematics

• Linear Function 100%
• Minimax 100%
• Conditionals 50%
• Upper Bound 50%
• Markov Process 50%
• Approximation Function 50%
• Statistical Theory 50%
• Iteration Method 50%

Keyphrases

• Optimistic Planning 50%
• Fitted Q-iteration 50%
• Conditional Mean Embedding 50%
• Martingale Concentration 50%
• Long-term Distribution 50%
• Safe Policy Improvement 50%
• Evaluation Errors 50%