AI Paper Atlas

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

Integrated Cooperation and Competition in Multi-Agent Decision-Making

Kyle Wray, Akshat Kumar, Shlomo Zilberstein

AAAI 2018 · Multi-agent systems and games › Cooperative multi-agent RL · approach: MARL benchmarks and grouping

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
increase controller nodes per agent from 2 to 4CCP approximate algorithm · Battle Meetingtotal computation time (sec.): 447.2 -> 2827.3Hurt
increase controller nodes per agent from 4 to 6CCP approximate algorithm · Battle Meetingtotal computation time (sec.): 2827.3 -> 10775.3Hurt
increase controller nodes per agent from 2 to 4CCP approximate algorithm · Prisoner Meetingtotal computation time (sec.): 574.1 -> 2577.0Hurt
increase controller nodes per agent from 4 to 6CCP approximate algorithm · Prisoner Meetingtotal computation time (sec.): 2577.0 -> 11702.8Hurt
increase controller nodes from 2 to 6CCP approximate algorithm · Battle Meetingbest response iterations: 10.5 -> 16.5Hurt
increase controller nodes from 2 to 6CCP approximate algorithm · Prisoner Meetingbest response iterations: 13.3 -> 38.3Hurt
increase controller nodes from 2 to 4CCP approximate algorithm · Battle Meetinggroup objective computation time (sec.): 17.6 -> 322.4Hurt
increase controller nodes from 4 to 6CCP approximate algorithm · Battle Meetinggroup objective computation time (sec.): 322.4 -> 181.5Improved
increase controller nodes from 2 to 6CCP approximate algorithm · Prisoner Meetingindividual objective computation time (sec.): 20.7 -> 182.2Hurt
increase allotted slack from 0 to 25CCP approximate algorithm · Battle Meetinggroup objective ADRHurt
increase allotted slack from 0 to 25CCP approximate algorithm · Battle Meetingindividual objective ADRImproved
increase allotted slack from 0 to 25CCP approximate algorithm · Prisoner Meetingindividual objective ADRHurt

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