AI Paper Atlas

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

ConTaCT: Deciding to Communicate during Time-Critical Collaborative Tasks in Unknown, Deterministic Domains

AAAI 2016 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Learned inter-agent communication · 33 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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
decide communication via alpha/beta/gamma reward estimates (ConTaCT) instead of communicating before using every new observation (RooC)multi-agent grid rescue · 10x10 grid, 5 agents, 50 trialstotal # communications: 112 -> 43Helped
ConTaCT vs RooC task successmulti-agent grid rescue · 10x10 grid, 5 agents, 50 trialssuccessful tasks (%): 78 -> 70Hurt
allow local replanning with unshared information and communication (ConTaCT) vs no communicationmulti-agent grid rescue · 10x10 grid, 5 agents, 50 trialssuccessful tasks (%): 52 -> 70Helped
ConTaCT vs RooC across grid sizes and communication costsmulti-agent grid rescue · all gridscommunication reduction: more than 60% reductionHelped
ConTaCT vs NC on large 25x25 gridmulti-agent grid rescue · 25x25 grid, 5 agents, 20 trials, -Ric=1successful tasks (%): 35 -> 35No 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