AI Paper Atlas

Research map / Reinforcement learning / Visual and representation RL

Think2Drive: Efficient Reinforcement Learning by Thinking with Latent World Model for Autonomous Driving (in CARLA-v2)

Qifeng Li, Xiaosong Jia, Shaobo Wang, Junchi Yan

ECCV 2024 · Reinforcement learning › Visual and representation RL · approach: RL for combinatorial routing · 84 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
replace model-free PPO with model-based RL in the expert (Think2Drive versus Roach-style PPO)expert driving planner · CornerCaseRepodriving score: 57.5 -> 83.8Improved
replace PPO with Think2Drive on official CARLA v2 routesexpert driving planner · CARLA Leaderboard v2driving score: 0.7 -> 56.8Improved
add reset technique (re-initialize planner parameters mid-training, Brick 1) (ablation)Think2Drive · CornerCaseRepo trainingsuccess rateImproved
add curriculum warm-up on simple lane following and turns (Brick 5) (ablation)Think2Drive · CornerCaseRepo trainingsuccess rateImproved
add termination-priority sampling (Brick 3) (ablation)Think2Drive · CornerCaseRepo trainingsuccess rateImproved
add steering cost function (Brick 4) (ablation)Think2Drive · CornerCaseRepo trainingsuccess rateImproved
increase planner train ratio to 4x the world model (Brick 6) (ablation)Think2Drive · CornerCaseRepo trainingsuccess rateImproved
distill Think2Drive expert into raw-sensor student (TCP)TCP student · CornerCaseRepodriving score: 83.8 -> 36.40Hurt
Think2Drive versus Roach on Leaderboard v1 official routesexpert driving planner · CARLA Leaderboard v1driving score: 84.0 -> 90.2Improved

Later papers that compared with this method

1 later accepted paper reports Think2Drive as a baseline in their results tables; 0 of them report a better number on most of the results they share with it.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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