AI Paper Atlas

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

Complexity of Derivative-Free Policy Optimization for Structured $\mathcal{H}_\infty$ Control

Xingang Guo, Darioush Keivan, Geir Dullerud, Peter Seiler, Bin Hu

NeurIPS 2023 · 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
model-free zeroth-order method vs model-based HIFOO on AC15Algorithm 1 · COMPleib AC15H-infinity norm: 15.2919 -> 15.4141No clear effect
model-free method vs HIFOO on HF2D11Algorithm 1 · COMPleib HF2D11H-infinity norm: 7.7237 × 104 -> 7.7223 × 104No clear effect
model-free method vs HIFOO on DLR2Algorithm 1 · COMPleib DLR2H-infinity norm: 4.0066 × 103 -> 4.0094 × 103No clear effect
model-free method vs HIFOO on HE4Algorithm 1 · COMPleib HE4H-infinity norm: 22.8382 -> 22.8538No clear effect
inexact instead of exact zeroth-order oracleAlgorithm 1 · random systemsrelative errorNo clear effect
larger system dimension nx = 10, 50, 100Algorithm 1 · random systemsrelative errorNo clear effect
decrease target epsilonAlgorithm 1 · random systemsoracle callsHurt

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