AI Paper Atlas

Research map / Multi-agent systems and games / Cooperative multi-agent RL

Multi-Agent Pointer Transformer: Seq-to-Seq Reinforcement Learning for Multi-Vehicle Dynamic Pickup-Delivery Problems

Zengyu Zou, Jingyuan Wang, Yixuan Huang, Junjie Wu

AAAI 2026 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping · 1 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 autoregressive joint decoding (ablation)MAPT · synth-XLObj.: 1905.8 -> 3227.5Improved
add autoregressive joint decoding (ablation)MAPT · dhrd-seObj.: 49.4 -> 78.9Improved
add informative priors (load balance, distance) (ablation)MAPT · synth-XLObj.: 1375.0 -> 3227.5Improved
add informative priors (ablation)MAPT · synth-SObj.: 175.2 -> 275.2Improved
add Relation-Aware Attention (ablation)MAPT · synth-SObj.: 270.9 -> 275.2Improved
add Relation-Aware Attention (ablation)MAPT · dhrd-seObj.: 77.1 -> 78.9Improved
use MAPT instead of MAPDP (independent decoding, no priors)MAPT · synth-SObj.: 157.5 -> 275.2Improved
use MAPT instead of Rolling-Horizon SAMAPT · synth-L inference timeseconds per instance: 166.660 -> 8.300Improved
use MAPT instead of Nearest ruleMAPT · dhrd-seObj.: 39.8 -> 78.9Improved
increase deferral prior beta to larger values (ablation)MAPT · synth-L, synth-XL, dhrd-tpe, dhrd-seObj.Hurt
use small non-zero beta (ablation)MAPT · dhrd-tpe, dhrd-seObj.Improved
MAPT versus Nearest on inference timeMAPT · synth-Sseconds per instance: 0.059 -> 1.420Hurt

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