AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Object-Aware Regularization for Addressing Causal Confusion in Imitation Learning

Jongjin Park, Younggyo Seo, Chang Liu, Li Zhao, Tao Qin, Jinwoo Shin, Tie-Yan Liu

NeurIPS 2021 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 3 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 object-aware masking that drops feature-map units sharing VQ-VAE discrete codesBehavioral cloning · Confounded Atari (27 environments)Mean HNS: 91.7% -> 105.6%Improved
Add object-aware masking that drops feature-map units sharing VQ-VAE discrete codesBehavioral cloning · Original Atari (27 environments)Mean HNS: 99.0% -> 114.9%Improved
Add object-aware masking that drops feature-map units sharing VQ-VAE discrete codesBehavioral cloning · CARLA daytime tasksSuccess rate: BC: 75.0 -> 87.0 (Straight); 43.0 -> 70.0 (One turn); 16.9 -> 35.7 (Navigation); 18.0 -> 30.0 (Navigation w/ dynamic obsImproved
Use fixed VQ-VAE representations instead of an action-trained encoder initialized from VQ-VAE (ablation)OREO behavioral cloning · Confounded Atari (8 selected environments)Mean HNS: 100.1% -> 41.3%Hurt
Replace object-aware masking with Dropout on fixed VQ-VAE representations (ablation)OREO behavioral cloning · Confounded Atari (8 selected environments)Mean HNS: 100.1% -> 45.7%Hurt
Replace object-aware masking with DropBlock on fixed VQ-VAE representations (ablation)OREO behavioral cloning · Confounded Atari (8 selected environments)Mean HNS: 100.1% -> 53.0%Hurt
Increase the per-code drop probability (ablation)OREO · Confounded Atari (8 environments)Mean HNSImproved
Use a codebook that is too small or too large (ablation)OREO · Confounded Atari (8 environments)Mean HNSHurt
Train with object-aware masking rather than plain behavioral cloning (ablation)OREO · Confounded Atari across varying demonstration sizesMean HNSImproved
Train the VQ-VAE from a very small demonstration set (N=5) (ablation)OREO · Confounded Atari (8 environments)Mean HNSMixed
Apply object-aware masking consistently across four stacked observationsBehavioral cloning · Confounded Atari (8 environments, four stacked observations)Mean HNS: 62.3% -> 87.4%Improved
Add OREO regularization to DRIL's behavioral-cloning policiesDRIL · Confounded CrazyClimber and PongSample efficiencyImproved

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