AI Paper Atlas

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

Learning Strategic Network Emergence Games

Rakshit Trivedi, Hongyuan Zha

NeurIPS 2020 · Multi-agent systems and games › Games and equilibria · approach: Opponent modeling in competitive games · 2 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
Transfer learned reward to larger network instead of training from scratchMINE · AndorraCorrect links (%): 76.5 -> 70.2Hurt
Transfer learned reward to larger Andorra networkMINE · AndorraTraining episodes: 100000 -> 72000Improved
Transfer reward across player sets in Trade networkMINE · TradeCorrect links (%): 87.2 -> 81Hurt
Transfer reward across player sets in Trade networkMINE · TradeTraining episodes: 25000 -> 18000Improved
Transfer reward across player sets in Movie bipartite networkMINE · MovieCorrect links (%): 62.54 -> 53.09Hurt
Transfer reward in Movie networkMINE · MovieTraining episodes: 60000 -> 45000Improved
Direct policy transfer without retraining instead of re-optimizing policy on transferred rewardMINE · TradeCorrect links (%): 81 -> 62.45Hurt
Direct policy transfer without retraining instead of re-optimizing policyMINE · AndorraCorrect links (%): 70.2 -> 68.88Hurt
Direct policy transfer without retraining instead of re-optimizing policyMINE · MovieCorrect links (%): 53.09 -> 51.1Hurt
Evaluate under perturbed graph (leaders swapped with followers) instead of policy-generated graph (ablation)MINE · Karate club, Leader#RedExpected return under learned payoff: -141.71 -> -221.4Hurt
Evaluate under perturbed graph instead of policy-generated graph (ablation)MINE · Karate club, Community#PurpleExpected return under learned payoff: -77.04 -> -101.65Hurt
Compare MINE with Social Game Embed on link predictionMINE · Arxiv GR-QCAUC: 0.855 vs 0.857Mixed

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