AI Paper Atlas

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

Truncated Counterfactual Learning for Anytime Multi-Agent Path Finding

Thomy Phan, Shao-Hung Chan, Sven Koenig

AAAI 2026 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Learning-guided MAPF search · 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
reset MABUC parameters when top-K set changes (non-stationarity) (ablation)TACKLE · Warehouse and City, 800 agentssum of delays and AUCImproved
use counterfactual TACKLE instead of interventional ADDRESSMAPF-LNS seed selection · Warehouse and City, 800 agentssum of delaysImproved
use TACKLE instead of observational Roulette Wheel or Tabu Listdelay-based MAPF-LNS · Warehouse and City, 800 agentssum of delaysImproved
use TACKLE instead of Roulette Wheel at m=1000delay-based MAPF-LNS · Warehousecost: at least 76% cost improvementImproved
use TACKLE instead of Roulette Wheel at m=1000delay-based MAPF-LNS · Citycost: at least 60% cost improvementImproved
use TACKLE instead of LaCAM*anytime MAPF · Warehousesum of delays: 70, 107.8 -> 411.1Improved
increase truncation K from 32 to 128 or more (ablation)ADDRESS · Warehouse and City, 800 agentssum of delaysHurt
increase truncation K to large values (ablation)TACKLE · Warehouse and City, 800 agentssum of delaysHurt
use TACKLE instead of baselines on small Random mapMAPF-LNS · Random-32-32-20sum of delaysNo 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