On the Value of Interaction and Function Approximation in Imitation Learning

Mathematics

• Approximation Function 100%
• Probability Theory 50%
• Worst Case 50%
• Optimal Policy 50%
• Linear Function 50%
• Time Step 50%
• Minimax 50%
• Confidence Set 50%

Computer Science

• Function Approximation 100%
• Learning Problem 33%
• Optimal Algorithm 33%
• Learning Algorithm 33%
• Multiclass Classification 33%
• Multi Class Classification 33%
• Linear Classifier 33%
• Linear Function 33%

Keyphrases

• Action Features 20%
• Parameter Sharing 20%
• Expert Trajectories 20%
• Play Actions 20%