AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Minimax Optimal Online Imitation Learning via Replay Estimation

Gokul Swamy, Nived Rajaraman, Matt Peng, Sanjiban Choudhury, Drew Bagnell, Steven Wu, Jiantao Jiao, Kannan Ramchandran

NeurIPS 2022 · 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
add replay estimation (RE) on top of online moment matching (MM)MM · PyBullet Walker, 12 expert trajectoriesexpert-normalized performanceImproved
add replay estimation to MM in a noisy-dynamics Walker with i.i.d. noise per timestepMM · Noisy PyBullet Walkerexpert-normalized performanceImproved
use the M_MAX membership oracle instead of M_RND or M_VAR (ablation)RE · PyBullet continuous controlperformance and correlation with ideal prefix weightsImproved
use RE instead of behavioral cloning under tiny noise in the initial velocityBC · PyBullet with perturbed initial velocityexpert-normalized performanceImproved
fix baseline tuning and implementation bugs after publicationMM and RE · Noisy environmentsexpert-normalized performanceMixed

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