AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Sequence Model Imitation Learning with Unobserved Contexts

NeurIPS 2022 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 3 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 history of length 5 to behavioral cloning (ablation)BC · HalfCheetahreturnHurt
Add history of length 5 to behavioral cloning (ablation)BC · AntreturnHurt
Add history of length 5 to DAgger (ablation)DAgger · HalfCheetahmoment-matching error (MSE)Helped
Add history of length 5 to DAgger (ablation)DAgger · Antmoment-matching error (MSE)Helped
Use on-policy interaction rather than off-policy behavioral cloningHistory-based imitation learning · Causal Banditexpert-relative mistakes: 1/5 success rate for the latching off-policy learnerHelped
Give the learner history while training off-policy on expert demonstrations (ablation)BC · PyBullet continuous controlreturnHurt
Treat the learner's past actions as interventions rather than expert-generated evidenceBayesian context inference · Causal Banditexpert-relative mistakesHelped

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