AI Paper Atlas

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

Surprise Minimizing Multi-Agent Learning with Energy-based Models

Karush Suri, Xiao Qi Shi, Konstantinos N Plataniotis, Yuri Andrew Lawryshyn

NeurIPS 2022 · Multi-agent systems and games › Cooperative multi-agent RL · approach: Cooperative MARL algorithms · 0 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 EMIX energy-based surprise minimization on top of QMIXQMIX · StarCraft II micromanagement (6 scenarios)success rate: 93.43 -> 94.90 (3m); 34.42 -> 37.07 (5m_vs_6m)Improved
add EMIX to QMIX on large-opponent scenarioQMIX · so_many_banelingsuccess rate: 93.35 -> 95.87Improved
add EMIX to QMIX on 10m_vs_11mQMIX · 10m_vs_11msuccess rate: 70.36 -> 75.35Improved
use EMIX energy-based surprise instead of SMiRL surprise in QMIXSMiRL-QMIX · StarCraft II micromanagementsuccess rate: 0.24 -> 97.22 (3s_vs_4z); 77.85 -> 75.35 (10m_vs_11m)Mixed
add EMIX to QMIX on Predator-Prey punishQMIX · predator_prey_punishaverage return: 14.33 -> 24.17Improved
add EMIX to QMIX on Predator-Prey hardQMIX · predator_prey_hardaverage return: 8.76 -> 12.34Improved
add EMIX to QMIX on easy Predator-Prey tasksQMIX · predator_prey_easy and predator_preyaverage return: 40.00 -> 40.00No clear effect
add energy operator on top of twin surprise approximators (TwinQMIX -> EMIX) (ablation)TwinQMIX · predator_prey_punishaverage return: 20.32 -> 24.17Improved
add energy operator on top of twin surprise approximators (TwinQMIX -> EMIX) (ablation)TwinQMIX · predator_prey_hardaverage return: 10.19 -> 12.34Improved
add twin surprise approximators to QMIX (TwinQMIX) (ablation)QMIX · 3 StarCraft II scenariosaverage success rateImproved
use dual (twin) approximators for surprise in EMIX (ablation)EMIX · 3 StarCraft II scenariosaverage success rateNo clear effect
add energy operator T to surprise value function (ablation)TwinQMIX · 5m_vs_6m and so_many_banelingaverage success rateImproved

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