AI Paper Atlas

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

Estimating α-Rank by Maximizing Information Gain

Tabish Rashid, Cheng Zhang, Kamil Ciosek

AAAI 2021 · Multi-agent systems and games › Games and equilibria · approach: Cooperation and social dilemmas · 4 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
Select payoff queries by information gain about the α-rank instead of payoff uncertaintyαIG (Bins) · 2 Good, 2 BadBayesian regretImproved
Select payoff queries by information gain about the α-rank instead of payoff uncertaintyαIG (Bins) · 4x4 GaussianregretImproved
Use the Wasserstein query objective instead of the entropy-based information-gain objectiveαIG · 2 Good, 2 BadBayesian regretImproved
Use the Binning entropy estimator instead of NSB (ablation)αIG · 3 Good, 5 BadBayesian regretImproved
Use the NSB entropy estimator (ablation)αIG · 3 Good, 5 BadBayesian regretHurt
Incorporate payoff antisymmetry and block-wise equality as prior knowledge (ablation)αIG · 3 Good, 5 Badsample efficiencyImproved
Incorporate payoff antisymmetry and block-wise equality as prior knowledge (ablation)αWass · 3 Good, 5 Badsample efficiencyImproved
Incorporate payoff antisymmetry and block-wise equality as prior knowledge (ablation)RG-UCB · 3 Good, 5 Badsample efficiencyHurt
Increase hallucinated-belief conditioning from once to 100 times (ablation)αIG · 2 Good, 2 Badseparation between query objective valuesImproved
Increase hallucinated-belief conditioning from once to 100 times (ablation)αWass · 2 Good, 2 Badseparation between query objective valuesImproved
Use direct information gain about α-ranks rather than information gain about the payoff distributionαIG · 2 Good, 2 Badrelevant-payoff samplingImproved
Use payoff information gain rather than direct α-rank information gainPayoff · 2 Good, 2 BadBayesian regretHurt

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