AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

Deep Imitative Models for Flexible Inference, Planning, and Control

Nicholas Rhinehart, Rowan McAllister, Sergey Levine

ICLR 2020 · Reinforcement learning › Imitation learning · approach: Behavior cloning theory and models · 56 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
Use an imitative trajectory-density prior with goal likelihood planningCARLA dynamic driving · Town01 and Town02success rateImproved
Use Gaussian Final-State Mixture goals instead of Final-State Indicator goals (ablation)Imitative Model · CARLA Dynamic Navigation, Town02success rate: 84% -> 100%Improved
Use Line Segment Final-State Indicator goals instead of Final-State Indicator goals (ablation)Imitative Model · CARLA Dynamic Navigation, Town02success rate: 84% -> 88%Improved
Use Region Final-State Indicator goals instead of Final-State Indicator goals (ablation)Imitative Model · CARLA Dynamic Navigation, Town02success rate: 84% -> 88%Improved
Add a smart waypointer that uses traffic-light state (ablation)Imitative Model with Region Final-State Indicator · CARLA Dynamic Navigation, Town01red-light violations: 56% -> 2.8%Improved
Add a smart waypointer that uses traffic-light state (ablation)Imitative Model with Gaussian Final-State Mixture · CARLA Dynamic Navigation, Town01success rate: 92% -> 100%Improved
Add test-time pothole costs (ablation)Imitative Model with Gaussian Final-State Mixture · CARLA pothole avoidance, Town01potholes hit: 177/230 -> 10/230Improved
Add test-time pothole costs (ablation)Imitative Model with Gaussian Final-State Mixture · CARLA pothole avoidance, Town02potholes hit: 82/154 -> 35/154Improved
Provide waypoints on the wrong side of the road (ablation)Imitative Model with Gaussian Final-State Mixture · CARLA robustness, Town01 and Town02success rate: 100%; 70%Mixed
Provide half of the waypoints as distractors (ablation)Imitative Model with Gaussian Final-State Mixture · CARLA robustness, Town01 and Town02success rate: 70%; 50%Mixed
Include traffic-light state in the trajectory model (ablation)R2P2-based Imitative Model · CARLA drivingred-light stopping preferenceImproved

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