AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Keyframe-Focused Visual Imitation Learning

Chuan Wen, Jierui Lin, Jianing Qian, Yang Gao, Dinesh Jayaraman

ICML 2021 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 0 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
Upweight action-changepoint frames using APE-based step weightsHistory-based behavioral cloning · CARLA NoCrash-Dense%success: 33.000 ± 4.190 -> 43.444 ± 0.786Improved
Upweight action-changepoint frames using APE-based step weightsHistory-based behavioral cloning · CARLA NoCrash-Dense without speed%success: 25.667 ± 0.981 -> 36.778 ± 5.808Improved
Use history rather than a single observationBehavioral cloning · CARLA NoCrash-Dense without speed%success: 9.222 ± 2.380 -> 25.667 ± 0.981Improved
Use history rather than a single observationBehavioral cloning · CARLA NoCrash-Dense%success: 42.667 ± 8.668 -> 33.000 ± 4.190Hurt
Apply APE-based softmax weighting rather than APE-based step weighting (ablation)Keyframe-focused behavioral cloning · Hopperreward: 905±135 -> 951±117Improved
Apply APE-based softmax weighting rather than APE-based step weighting (ablation)Keyframe-focused behavioral cloning · HalfCheetahreward: 470 ± 205 -> 819 ± 96Improved
Apply APE-based softmax weighting rather than APE-based step weighting (ablation)Keyframe-focused behavioral cloning · Walker2Dreward: 654±53 -> 769±97Improved
Replace APE-based weighting with Bayesian changepoint detection weighting (ablation)Keyframe-focused behavioral cloning · CARLA NoCrash-Dense%success: 43.444 ± 0.786 -> 28.667 ± 2.494Hurt
Replace APE-based weighting with action-category frequency weighting (ablation)Keyframe-focused behavioral cloning · CARLA NoCrash-Dense%success: 43.444 ± 0.786 -> 20.333 ± 5.825Hurt
Replace APE-based weighting with AdaBoost-style reweighting (ablation)Keyframe-focused behavioral cloning · CARLA NoCrash-Dense%success: 43.444 ± 0.786 -> 3.000 ± 1.414Hurt
Omit ego velocity from the input observationsSingle-observation behavioral cloning · CARLA NoCrash-Dense%success: 42.667 ± 8.668 -> 9.222 ± 2.380Hurt
Use 1k expert queries with DAGGER rather than offline APE-weighted imitationBehavioral cloning · HalfCheetahreward: 819 ± 96 -> 822 ± 186Improved

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