AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Learning To Drive From a World on Rails

Dian Chen, Vladlen Koltun, Philipp Krähenbühl

ICCV 2021 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 128 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 camera augmentation (ablation)Rails · NoCrash Dense (test town, test weather)success rate (%): 42 -> 48Improved
add speed augmentation (ablation)Rails · NoCrash Dense (test town, test weather)success rate (%): 42 -> 58Improved
add both camera and speed augmentation (ablation)Rails · NoCrash Dense (test town, test weather)success rate (%): 42 -> 66Improved
add camera augmentation on top of speed augmentation (ablation)Rails · NoCrash Dense (test town, train weather)success rate (%): 64 -> 74Improved
add camera augmentation on top of speed augmentation (ablation)Rails · NoCrash Dense (train town, test weather)success rate (%): 80 -> 84Hurt
add auxiliary semantic segmentation loss (ablation)Rails · NoCrash Empty (test town, test weather)success rate (%): 46 -> 76Improved
add auxiliary semantic segmentation loss (ablation)Rails · NoCrash Empty (train town, test weather)success rate (%): 70 -> 100Improved
add factorized world model (F-DM instead of DM) (ablation)Dreamer · CoRL17 / NoCrashsuccess rate (%): 37 -> 44 (Straight, train town); 0 -> 0 (Turn)Mixed
add tabular Bellman distillation instead of CEM planning (ablation)Rails · NoCrash Dense (test town, train weather)success rate (%): 47 -> 74Improved
add world-on-rails factorization instead of full world model (Dreamer) (ablation)Rails · CoRL17 Turn (train town)success rate (%): 0 -> 100Improved
add Ornstein-Uhlenbeck noise to training trajectories (with both augmentations) (ablation)Rails · NoCrash Dense (test town, test weather)success rate (%): 66 -> 46No clear effect
add Rails instead of IA in traffic light complianceRails · NoCrash Dense (train town, train weather)traffic light violations per hour: 15.41 -> 2.61Improved

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