AI Paper Atlas

Research map / Reinforcement learning / Imitation learning

CoIRL-AD: Collaborative-Competitive Imitation-Reinforcement Learning in Latent World Models for Autonomous Driving

Xiaoji Zheng, Ziyuan Yang, Yanhao Chen, Yuhang Peng, Yuanrong Tang, Gengyuan Liu, Bokui Chen, Jiangtao Gong

ICML 2026 · Reinforcement learning › Imitation learning · approach: Imitation combined with RL

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 RL actor with latent world model and competition on top of LAWLAW · nuScenesavg L2 x Col: 0.15 -> 0.11Improved
add competition between IL and RL actors (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.21 -> 0.11Improved
decouple IL and RL into separate actors rather than merging losses (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.17 -> 0.11Improved
use two-stage IL then RL fine-tuning (ablation)LAW · nuScenesavg L2 x Col: 0.15 -> 18.23Hurt
use inverse causal mask in planning head (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.18 (AR) -> 0.11Improved
use inverse causal mask on pure IL baseline (ablation)LAW · nuScenesavg L2 x Col: 0.15 -> 0.18Hurt
use mismatched masks for IL and RL actors (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.11 -> 0.15Hurt
add latent world model to RL imagination (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.13 -> 0.11Improved
add small behavior cloning regularizer (beta 0.005) (ablation)RL actor · nuScenesavg L2 x Col: 0.13 -> 0.11Improved
train RL only without IL (ablation)RL actor · nuScenesavg L2 x Col: 0.15 -> 32.29Hurt
use CQL pure offline RL instead of world-model RL (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.11 -> 15.87Hurt
use PPO-lite instead of group-sampled policy gradient (ablation)CoIRL-AD · nuScenesavg L2 x Col: 0.11 -> 0.10No clear effect

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