AI Paper Atlas

Research map / Reinforcement learning / Policy gradient and actor-critic

Independent Policy Gradient Methods for Competitive Reinforcement Learning

Constantinos Daskalakis, Dylan J Foster, Noah Golowich

NeurIPS 2020 · Reinforcement learning › Policy gradient and actor-critic · approach: Variance-reduced policy gradients · 21 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
Use two-timescale learning rates, with one player updating much more slowlyIndependent policy gradient in two-player zero-sum stochastic games · Two-player zero-sum stochastic gamesaverage min-player Nash gapImproved
Use equal learning rates instead of two-timescale updatesIndependent gradient descent-ascent · Zero-sum matrix gamesdistance of individual iterates from equilibriumHurt
Use ε-greedy exploration with direct policy parameterizationIndependent policy gradient · Two-player zero-sum stochastic gamesREINFORCE gradient-estimator variance: 24\frac{A^{2}}{\varepsilon_x\zeta^{4}}Improved
Apply extragradient updatesRatio games and randomly generated multi-state stochastic games · Stochastic gameslast-iterate convergenceMixed

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