Which imitation-learning algorithm overcomes behavioral cloning's compounding errors by iteratively rolling out the current policy, having an expert label the states it visits, and aggregating those into the training set?

Show answer

DAgger (Dataset Aggregation)

Introduced by Ross, Gordon, and Bagnell in 2011, DAgger (Dataset Aggregation) attacks the distribution shift that makes naive cloning's errors compound. By repeatedly relabeling the states the learner itself visits, it keeps the training distribution aligned with the policy's own state distribution.

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

Which large-scale image database supplied the 1,000-class dataset used in the 2012 ILSVRC competition?
Which loss function is the standard choice for training a neural network for multi-class classification with a Softmax output layer?
Which neural network activation function can lead to 'dead' neurons because its gradient is zero for all negative inputs?
Which optimization algorithm combines the benefits of both AdaGrad and RMSProp by using both momentum and adaptive learning rates?
Which regularization technique prevents overfitting by randomly setting a fraction of input neurons to zero during each training step?
Which researcher, who co-authored the 2012 AlexNet paper, later became the Chief Scientist at OpenAI?

See all 98 →