In imitation learning, a behavioral-cloning policy with small per-step error can accumulate total error growing quadratically with the horizon T; DAgger's no-regret formulation reduces this growth to what order in T?

Show answer

Linear (order T)

Ross and Bagnell showed a cloning policy with per-step error epsilon can incur total error scaling like epsilon times T-squared, because each mistake carries the agent into unfamiliar states. Casting imitation as online learning, DAgger brings the bound down to roughly linear in T.

Would you remember this in 6 months?

Trivia Forge uses spaced repetition so facts stick. Free, no signup needed.

Turn on Machine Learning practice →

More Machine Learning trivia

In mechanistic interpretability, what type of model is trained on a network's internal activations to decompose them into a large set of sparse, more human-interpretable features, helping address superposition?
In Principal Component Analysis (PCA), the principal components are the eigenvectors of which specific matrix?
In Reinforcement Learning, what equation expresses the value of a state as the expected immediate reward plus the discounted value of the next state?
In Reinforcement Learning, what is the term for the tension between trying new actions to find better rewards and choosing known actions that yield high rewards?
In Support Vector Machines, what is the 'Kernel Trick' used to achieve?
In the Bias-Variance Tradeoff, what component of error is reduced by increasing model complexity?

See all 98 →