AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Distributionally Robust Imitation Learning

Mohammad Ali Bashiri, Brian D Ziebart, Xinhua Zhang

NeurIPS 2021 · Reinforcement learning › Imitation learning · approach: Offline imitation from imperfect data · 1 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
convex optimization instead of double oracleDROIL · GridWorld size 128training time (s): 30.1 -> 1.6Improved
convex optimization instead of double oracleDROIL · GridWorld size 2000training time (s): 608.1 -> 98.6Improved
convex optimization instead of double oracleDROIL · GridWorld size 5500training time (s): 4970 -> 881Improved
convex optimization instead of double oracleDROIL · GridWorld size 432cost: −21.74 -> −21.61No clear effect
convex optimization instead of double oracleDROIL · GridWorld size 5500cost: −58.9 -> −58.7No clear effect
Euclidean loss instead of 0-1, action, or random loss (ablation)DROIL · GridWorldmisprediction rateImproved
more demonstrationsMMP and Abbeel & Ng · highway drivingvalue differenceHurt
DROIL instead of MMP, Abbeel & Ng, LEARCHDROIL · highway driving (original and transfer)value difference and misprediction rateImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy