AI Paper Atlas

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

SPACeR: Self-Play Anchoring with Centralized Reference Models

Wei-Jer Chang, Akshay Rangesh, Kevin Joseph, Matthew Strong, Masayoshi Tomizuka, yihan hu, Wei Zhan

ICLR 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Data-driven traffic simulation · 5 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
anchor self-play to a pretrained tokenized reference model (SPACeR vs PPO)self-play PPO · WOSAC val (vehicles)composite realism: 0.710 -> 0.741Improved
anchor self-play to reference modelself-play PPO · WOSAC val (vehicles)minADE: 12.725 -> 4.101Improved
add KL alignment to reference (Goal + KL vs Goal + LLH) (ablation)SPACeR · WOSAC val (vehicles, anchoring ablation)composite realism: 0.69 -> 0.73Improved
add log-likelihood reward only on top of task reward (ablation)SPACeR · WOSAC val (vehicles, anchoring ablation)composite realism: 0.70 -> 0.69No clear effect
add log-likelihood reward on top of KL + infraction penalties (ablation)SPACeR · WOSAC val (vehicles, anchoring ablation)composite realism: 0.74 -> 0.74No clear effect
remove explicit goal reward when anchored (KL + r_inf vs Goal + KL) (ablation)SPACeR · WOSAC val (vehicles, anchoring ablation)composite realism: 0.73 -> 0.74Improved
remove reference KL loss (ablation)SPACeR · WOSAC val (pedestrians and cyclists)composite realism: 0.607 -> 0.729 (adding KL)Improved
add multi-action head (ablation)SPACeR · WOSAC val (pedestrians and cyclists)composite realism: 0.685 -> 0.729Improved
add goal-reaching weight (ablation)SPACeR · WOSAC val (pedestrians and cyclists)composite realism: 0.728 -> 0.729No clear effect
use weaker 0.3M reference model (ablation)SPACeR · WOSAC val (vehicles)composite realism: 0.636 reference -> 0.732 SPACeRNo clear effect
replace imitation model with SPACeR policyCAT-K / SMART · WOSAC val (vehicles)throughput (scenarios/s): 22.5 -> 211.8Improved
SPACeR vs CAT-K on composite realismSPACeR · WOSAC val (vehicles)composite realism: 0.766 -> 0.741Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

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