AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

On the Global Convergence Rates of Decentralized Softmax Gradient Play in Markov Potential Games

Runyu Zhang, Jincheng Mei, Bo Dai, Dale Schuurmans, Na Li

NeurIPS 2022 · Optimization › Nonconvex and smooth optimization · approach: Equilibrium learning in zero-sum games

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 log-barrier regularization to softmax gradient playGradient play · bad initialization near non-NE stationary pointconvergence to Nash equilibriumImproved
add log-barrier regularization to softmax natural gradient playNatural gradient play · two-player identical-reward matrix gameescape from non-NE stationary regionsImproved
use natural gradient play instead of gradient playSoftmax policy parameterization · two-player identical-reward matrix gameconvergence speedImproved
add log-barrier regularization to natural gradient playNatural gradient play · two-player identical-reward matrix gamenumerical stabilityHurt
start from uniform initialization without regularizationGradient play and natural gradient play · two-player identical-reward matrix gameNE gapHurt
add log-barrier regularizationSoftmax gradient play · iteration complexity bounddependence on action set sizeHurt

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