Research map / Bandits and online learning / Online convex optimization and games
Learning to Crawl
Utkarsh Upadhyay, Robert Busa-Fekete, Wojciech Kotlowski, David Pal, Balazs Szorenyi
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 |
|---|---|---|---|
| Choose the exploration horizon to scale as O(√T) | Explore-and-commit · MSMARCO, simulated web crawling | normalized regret: 1/√T | Improved |
| Use phased ε-greedy instead of ETC | Web-crawling policy · MSMARCO, simulated web crawling | regret | Mixed |
| Use the moment-matching estimator instead of the MLE estimator | Poisson change-rate estimation from partial observations · Simulated and real data | estimation error | No clear effect |
| Use uniform-interval exploration instead of uniform-rate exploration | ETC exploration phase · Web crawling, exploration phase | regret | Improved |
Closest papers by meaning
- Staying up to Date with Online Content Changes Using Reinforcement Learning for Scheduling (NeurIPS 2019 · similarity 0.83)
- Online Weighted Paging with Unknown Weights (NeurIPS 2024 · similarity 0.82)
- TimeWarp: Evaluating Web Agents by Revisiting the Past (NeurIPS 2026 · similarity 0.81)
- Go-Browse: Training Web Agents with Structured Exploration (ICLR 2026 · similarity 0.80)
- Web-Shepherd: Advancing PRMs for Reinforcing Web Agents (NeurIPS 2025 · similarity 0.79)
- A Simple and Adaptive Learning Rate for FTRL in Online Learning with Minimax Regret of $\Theta(T^{2/3})$ and its Application to Best-of-Both-Worlds (NeurIPS 2024 · similarity 0.79)
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.
