Dagger
Software / App
An iterative algorithm for addressing covariate shift in imitation learning by aggregating expert relabeling of states visited by the learner policy.
Mentioned in 2 videos
Save the 2 videos on Dagger to your own pod.
Sign up free to keep building your knowledge base on Dagger as more episodes are added.
Videos Mentioning Dagger
Robot-Use Agents: Why General-Purpose Models May Win in Robotics
Y Combinator
A framework for data aggregation in reinforcement learning, used as an analogy for how AI systems might compress and train weights during a 'sleep' phase.
Stanford AA203 Optimal and Learning-Based Control | Spring 2026 | Lecture 15: Imitation Learning
Stanford Online
An iterative algorithm for addressing covariate shift in imitation learning by aggregating expert relabeling of states visited by the learner policy.