AI Paper Atlas

Research map / Multi-agent systems and games / Games and equilibria

Learning NP-Hard Multi-Agent Assignment Planning using GNN: Inference on a Random Graph and Provable Auction-Fitted Q-learning

HYUNWOOK KANG, Taehwan Kwon, Jinkyoo Park, James R. Morrison

NeurIPS 2022 · Multi-agent systems and games › Games and equilibria · approach: Learning with strategic agents · 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
compare against Gurobi optimal on linear deterministic MRRCOTAP + AFQI · MRRC linear deterministicreward ratio rho (%): 95.35 to 98.31 of optimal (range over sizes)Hurt
zero-shot transfer to larger problems (train 2R/20T, test 8R/50T)OTAP + AFQI · MRRC linear deterministicreward ratio rho (%): 96.85 -> 93.44Hurt
zero-shot transfer to smaller problems (train 8R/50T, test 3R/30T)OTAP + AFQI · MRRC linear deterministicreward ratio rho (%): 97.35No clear effect
use stochastic instead of deterministic travel timesOTAP + AFQI · MRRC linear, 2R/20T vs SGAreward ratio rho (%): 137.3 -> 130.9No clear effect
use nonlinear instead of linear decaying rewardsOTAP + AFQI · MRRC deterministic, 2R/20T vs SGAreward ratio rho (%): 137.3 -> 111.5Mixed
OTAP + AFQI instead of Ekici et al. heuristicOTAP + AFQI · MRRC linear deterministicreward ratio rho (%): 99.86 -> 118.33Mixed
OTAP + AFQI instead of SGAOTAP + AFQI · MRRC linear deterministic, 8R/50Treward ratio rho (%): 119.8Improved
increase problem size (tasks/robots) during trainingAFQI · MRRC linear deterministictraining time to 93% optimality: 19261.2 -> 99032.7No clear effect
increase number of tasks in IPMS from 50 to 100 (3 machines)Ours · IPMSmakespan ratio vs OR-Tools: 106.7% -> 100.7%Improved
increase machines from 3 to 10 at 100 tasks in IPMSOurs · IPMSmakespan ratio vs OR-Tools: 100.7% -> 109.0%Hurt
compare with Google OR-Tools on minimax mTSPOurs · minimax mTSPaverage ratio to CPLEX: 1.0180 -> 1.0268Hurt
use random-graph structure2vec with OTAP instead of exact argmax in FQIAFQI · theoryperformance guarantee: 1-1/eImproved

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