atlas

Research map / Learning theory and algorithms / Submodular and game algorithms

Optimistic Regret Minimization for Extensive-Form Games via Dilated Distance-Generating Functions

NeurIPS 2019 · Learning theory and algorithms › Submodular and game algorithms · approach: Zero-sum game learning dynamics · 13 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
Use optimistic regret minimization with a dilated Euclidean DGF instead of CFR/CFR+Smallmatrix · Smallmatrixsaddle-point gap: up to 12 orders of magnitude better-approximate saddle-pointsHelped
Use CFR+Smallmatrix · Smallmatrixsaddle-point gap convergence rate: $T^{-0.7375}$Hurt
Use OFTRL instead of CFR+Leduc poker · Leduc pokersaddle-point gapHurt
Use OFTRL instead of CFR+Leduc poker · Leduc pokersum of cumulative regretsHelped
Use optimistic regret minimization instead of CFR+Deep game trees · Deep game treessum of cumulative regretsHelped
Use optimistic OMD instead of OFTRLLeduc poker · Leduc pokersum of cumulative regretsHurt
Use optimistic OMD with dilated Euclidean DGFKuhn poker · Kuhn pokerlast-iterate saddle-point gapHelped

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