AI Paper Atlas

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

The Benefits of Being Distributional: Small-Loss Bounds for Reinforcement Learning

Kaiwen Wang, Kevin Zhou, Runzhe Wu, Nathan Kallus, Wen Sun

NeurIPS 2023 · 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
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · King County Housing, All episodesaverage cost: .734 (.0007) -> .726 (.0003)Improved
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · King County Housing, Last 100 ep.average cost: .719 (.0013) -> .708 (.0019)Improved
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · Prudential Life Insurance, All episodesaverage cost: .491 (.0029) -> .411 (.0038)Improved
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · Prudential Life Insurance, Last 100 ep.average cost: .474 (.0111) -> .388 (.0086)Improved
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · CIFAR-100, All episodesaverage cost: .856 (.0016) -> .838 (.0021)Improved
Learn conditional cost distributions with online MLE and use their means for action selection instead of FastCB's direct mean estimationDistCB · CIFAR-100, Last 100 ep.average cost: .793 (.0031) -> .775 (.0027)Improved

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