AI Paper Atlas

Research map / Bandits and online learning / RL theory and MDPs

Stabilizing Q-learning with Linear Architectures for Provable Efficient Learning

Andrea Zanette, Martin Wainwright

ICML 2022 · Bandits and online learning › RL theory and MDPs · approach: Linear function approximation in RL · 0 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
Add policy replay to keep Q-learning updates on data from a stationary mixture of past policiesSequentially Stabilized Second-order Streaming Q-learning · Exploratory learning in low-rank MDPsregretImproved
Add a second-order update instead of a first-order updateStabilized, Second-Order, Streaming Q-learning · Stationary-controller learningstatistical efficiency: a rate $1/\sqrt{n}$ instead of the $1/n$Improved
Use target networks to hold the bootstrapped target fixed during each update epochStabilized, Second-Order, Streaming Q-learning · Linear function approximationstabilityImproved
Remove policy replay and update using a changing data distributionSequentially Stabilized Second-order Streaming Q-learning · Exploratory learning with linear function approximationstabilityHurt
Use policy replay rather than storing and replaying the full transition datasetSequentially Stabilized Second-order Streaming Q-learning · Exploratory learningmemory complexity: grows only logarithmically with sample sizeImproved

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