AI Paper Atlas

Research map / Optimization / Nonconvex and smooth optimization

Provably Efficient Neural GTD for Off-Policy Learning

Hoi-To Wai, Zhuoran Yang, Zhaoran Wang, Mingyi Hong

NeurIPS 2020 · Optimization › Nonconvex and smooth optimization · approach: Coordinate and Adam convergence analysis · 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
replace neural TD with neural GTD (primal-dual min-max) for off-policy learning2-layer ReLU NN · Garnet MDP, |S|=500, |A|=5, gamma=0.9average MSBE vs. width mImproved
neural TD under off-policy data as width m increasesneural TD · Garnet MDP, |S|=500, |A|=5, gamma=0.9average MSBE vs. width mNo clear effect
increase number of neurons mneural GTD · Garnet MDP off-policyaverage MSBEImproved

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