Research map / Probabilistic and scientific modeling / Bayesian optimization
Safe Exploration for Interactive Machine Learning
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use GoOSE's goal-directed safe exploration rather than safe-set-wide exploration | Safe Bayesian optimization with GP-UCB · Safe Bayesian optimization, 1D and 2D GP samples | ε-safe average regret | Helped |
| Use GoOSE for exploration instead of SMDP | Safe shortest path in synthetic deterministic MDPs · Synthetic grid worlds | samples to discover first path: a factor 2.5 fewer samples | Helped |
| Optimize sample efficiency with GoOSE rather than minimizing exploration trajectory cost with SEO | Safe shortest path in synthetic deterministic MDPs · Synthetic grid worlds | exploration trajectory cost | Hurt |
| Use GoOSE rather than SEO | Safe shortest path in deterministic MDPs · Synthetic grid worlds | computation time per iteration | Helped |
| Use goal-oriented safe exploration instead of SMDP | Safe shortest path in deterministic MDPs · Mars exploration | performance relative to SMDP | Helped |
| Use SEO rather than GoOSE | Safe shortest path in deterministic MDPs · Synthetic grid worlds | exploration trajectory cost | Helped |
Closest papers by meaning
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.85)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.84)
- Learning Safe Control via On-the-Fly Bandit Exploration (ICML 2025 · similarity 0.84)
- Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability (NeurIPS 2024 · similarity 0.84)
- Random Exploration in Bayesian Optimization: Order-Optimal Regret and Computational Efficiency (ICML 2024 · similarity 0.84)
- Principled Bayesian Optimization in Collaboration with Human Experts (NeurIPS 2024 · similarity 0.84)
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.