AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

Modelling Competitive Behaviors in Autonomous Driving Under Generative World Model

Guanren Qiao, Guiliang Liu, Guorui Quan, Rongxiao Qu

ECCV 2024 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 4 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
model competitive interaction with CCE-MASAC (optimistic value plus magnetic mirror descent) instead of MASACCCE-MASAC · Argoverse 2 scenarios (4 hold-out scenarios)CCE-gapImproved
use multi-agent game-theoretic training instead of supervised trajectory prediction (QCNet, GameFormer)CCE-MASAC · Argoverse 2 scenarios (4 hold-out scenarios)CCE-gapImproved
use MAPPO instead of soft actor-critic based MARLMAPPO baseline · Argoverse 2 scenariosCCE-gapHurt
train single-agent SAC inside the world model instead of behavior cloninggenerative world model · Argoverse 2 scenariosdiscounted cumulative rewardImproved
move from single-agent SAC to multi-agent CCE-MASAC (competitive interaction)world model agents · Argoverse 2 scenariosdiscounted cumulative rewardHurt

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