AI Paper Atlas

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

On the Computational Limits of AI4S-RL : A Unified $\varepsilon$-$N$ Analysis

Qili Shen, Kairui Feng, Ang He, Xuanhong Chen, Dake Zhang

ICLR 2026 · Reinforcement learning › Policy gradient and actor-critic · approach: Model-based RL with guarantees

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
move resolution parameters away from the optimum (K=1.5, log ratio 1/3) in tabular RL (ablation)tabular RL on Cart-Pole · Cart-Pole sample complexitysamples to 1% value error: 4500 -> 46000Hurt
off-optimal resolution choices instead of optimal ones (ablation)tabular RL and Q-learning on Cart-Pole · Cart-Pole sample complexitycomputational cost: N^1.6Hurt
use Q-learning with function approximation instead of tabular RLCart-Pole resolution study · Cart-Pole sample complexitysamples to 1% value error: 4500 -> 450Improved
increase surrogate resolution monotonically (ablation)tabular RL on Cart-Pole · Cart-Pole sample complexitylog10(N): 3.65 -> 4.66Mixed
coarsen spatial ratio to K=8.0 (ablation)PPO on Teppanyaki heat sequencing · Teppanyaki PDE controlconvergence: K = 8.0 fail to convergeHurt
choose theory-predicted K*=6 and log ratio 1/3PPO on Teppanyaki heat sequencing · Teppanyaki PDE controltotal computational cost: K*=6, loghw(hr)=1/3 minimum total costImproved

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