Research map / Bandits and online learning / Online convex optimization and games
Online Non-stochastic Control with Partial Feedback
Yu-Hu Yan, Peng Zhao, Zhi-Hua Zhou
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add the meta-base ensemble framework with a switching cost regularizer (PRONC) to bandit gradient descent control | BGD.Control · Synthetic time-varying LDS | cumulative cost | Improved |
| add the switching cost regularizer to the ensemble (ablation) | PBGD.Control · Synthetic time-varying LDS | cumulative cost | Improved |
| use PRONC-Select instead of PRONC-Combine when costs change gradually (large path length) | PRONC · Synthetic time-varying LDS | cumulative cost | Improved |
| use PRONC-Combine instead of PRONC-Select when costs change abruptly (small path length) | PRONC · Synthetic time-varying LDS | cumulative cost | Improved |
| give full-information gradients (Grad skylines) instead of one-point gradient estimates | PRONC · Synthetic time-varying LDS | cumulative cost | Improved |
| apply PRONC with periodic restarts to nonlinear tasks | PRONC · Pendulum, cartpole, data center cooling | cumulative cost | Improved |
Closest papers by meaning
- Non-stationary Online Learning with Memory and Non-stochastic Control (JMLR 2023 · similarity 0.94)
- Making Non-Stochastic Control (Almost) as Easy as Stochastic (NeurIPS 2020 · similarity 0.92)
- Online Control with Adversarial Disturbance for Continuous-time Linear Systems (NeurIPS 2024 · similarity 0.91)
- Online Control of Unknown Time-Varying Dynamical Systems (NeurIPS 2021 · similarity 0.90)
- Near-optimal Regret Using Policy Optimization in Online MDPs with Aggregate Bandit Feedback (ICML 2025 · similarity 0.88)
- Online Non-convex Learning in Dynamic Environments (NeurIPS 2024 · similarity 0.87)
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.
