AI Paper Atlas

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

Accelerating Quadratic Optimization with Reinforcement Learning

Jeffrey Ichnowski, Paras Jain, Bartolomeo Stellato, Goran Banjac, Michael Luo, Francesco Borrelli, Joseph E. Gonzalez, Ion Stoica, Ken Goldberg

NeurIPS 2021 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees · 20 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 vector rho adaptation instead of scalar rho adaptationRLQP · QPLIBsolve time (s): 205.372 -> 24.083 (instance 8559)Improved
use general RLQP (vector) instead of OSQP heuristicOSQP · QPLIBsolve time (s): 59.648 -> 24.083 (instance 8559)Mixed
use general RLQP (vector) instead of OSQP heuristicOSQP · Netlib LPshifted geomean speedup: 1.30xImproved
use general RLQP (vector) instead of OSQP heuristicOSQP · Maros-Meszarosshifted geomean runtime: 1.829Improved
train policy specific to the problem class instead of general benchmark policyRLQP · GOMP SQP QPsshifted geomean vs OSQP: 1.37Improved
train on low-dimensional problems only (10-50) vs full range (10-2000) (ablation)RLQP vector policy · Random QP, dimension scalingsolve timeHurt
include primal and dual residuals in policy state (Vector 1 vs 2) (ablation)RLQP vector policy · benchmark QPsgeomean solve timeNo clear effect
use 3 hidden layers instead of 2 (Vector 2 vs 3) (ablation)RLQP vector policy · benchmark QPsgeomean solve timeNo clear effect
tune training (smaller buffer, lower lr, larger batch, longer training) (ablation)RLQP vector policy · Netlib LPshifted geomean speedup: 1.23x -> 1.30xImproved

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