Research map / Reinforcement learning / Policy gradient and actor-critic
Efficient Nonmyopic Active Search
Shali Jiang, Gustavo Malkomes, Geoff Converse, Alyssa Shofner, Benjamin Moseley, Roman Garnett
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 |
|---|---|---|---|
| ENS instead of two-step lookahead | Active search · CiteSeerx, budget 500 | targets found at termination: 155 -> 189 | Improved |
| ENS with budget-matched horizon (ENS-100) vs ENS-900 after 100 queries (ablation) | ENS · CiteSeerx, 100 queries | targets found: 25.9 -> 30.7 | Improved |
| ENS instead of two-step lookahead | Active search · CiteSeerx, budget 100 | targets found: 24.9 -> 30.7 | Improved |
| ENS instead of two-step lookahead | Active search · BMG, budget 500 | targets found: 452 -> 466 | Improved |
| ENS with full budget 900 instead of two-step | Active search · BMG, 900 queries | targets found: 802 -> 815 | Improved |
| ENS-900 vs two-step at 100 queries (ablation) | ENS · BMG, 100 queries | targets found: 91.0 -> 89.0 | Hurt |
| ENS instead of two-step lookahead | Active search · Drug screening ECFP4 | active compounds found: 297 -> 303 | Improved |
| ENS instead of two-step lookahead | Active search · Drug screening GpiDAPH3 | active compounds found: 261 -> 276 | Improved |
| two-step lookahead instead of one-step greedy | Active search · Drug screening ECFP4 | active compounds found: 289 -> 297 | Improved |
| active search policies instead of stratified-sample 100-NN classifier | Active search · Drug screening ECFP4 | active compounds found: 189 -> 303 | Improved |
| random-greedy (RG) instead of 100-NN baseline | Random-greedy · Drug screening GpiDAPH3 | active compounds found: 134 -> 170 | Improved |
| ENS pruning of unlabeled points (ablation) | ENS · Drug screening | runtime | Improved |
Closest papers by meaning
- Active Learning of General Halfspaces: Label Queries vs Membership Queries (NeurIPS 2024 · similarity 0.84)
- Geometric Active Exploration in Markov Decision Processes: the Benefit of Abstraction (ICML 2024 · similarity 0.84)
- SeeA*: Efficient Exploration-Enhanced A* Search by Selective Sampling (NeurIPS 2024 · similarity 0.84)
- Active Classification with Few Queries under Misspecification (NeurIPS 2024 · similarity 0.84)
- AutoAL: Automated Active Learning with Differentiable Query Strategy Search (ICML 2025 · similarity 0.83)
- Learning-Augmented Search Data Structures (ICLR 2025 · similarity 0.83)
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.
