AI Paper Atlas

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

Provable Model-based Nonlinear Bandit and Reinforcement Learning: Shelve Optimism, Embrace Virtual Curvature

Kefan Dong, Jiaqi Yang, Tengyu Ma

NeurIPS 2021 · Bandits and online learning › RL theory and MDPs · approach: Linear function approximation in RL · 4 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 ViOlin's virtual ascent with online model learning and reward, gradient, and Hessian predictionNonlinear bandit with deterministic reward · Nonlinear banditlocal regret: \calO(\sqrt{T\mathfrak{R}_T}/\epsilon^2)Improved
Use ViOlin for RL with online dynamics learningModel-based RL with deterministic dynamics and reward · Nonlinear RLlocal regret: \calO(\sqrt{T\mathfrak{R}_T}/\epsilon^2)Improved
Use optimism-in-face-of-uncertainty with a two-layer neural net hypothesis classUCB on a linear ground-truth reward · Linear ground-truth reward, two-layer neural net hypothesissample complexity: exponential sample complexityHurt

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