Research map / Probabilistic and scientific modeling / Bayesian optimization
Threshold Learning for Optimal Decision Making
Nathan F Lepora
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 |
|---|---|---|---|
| use Bayesian optimization instead of REINFORCE to learn thresholds | threshold learning · Single learning episode | trials to convergence: 5000 -> 500 | Improved |
| use Bayesian optimization instead of REINFORCE | threshold learning · One-threshold learning | threshold uncertainty (1 s.d.): 0.23 -> 0.75 | Hurt |
| use Bayesian optimization instead of REINFORCE | threshold learning · One-threshold learning | computation time: 0.5 sec (5000 trials) -> 50 sec (500 trials) | Hurt |
| use Bayesian optimization instead of REINFORCE | threshold learning · One-threshold learning | computation time per trial: 0.1 msec/trial -> 100 msec/trial | Hurt |
| vary REINFORCE learning rate beta within 0.1-1 (ablation) | REINFORCE · One-threshold learning | threshold estimate | No clear effect |
| increase the number of binary units n (ablation) | REINFORCE · One-threshold learning | threshold variance | No clear effect |
| add reinforcement comparison reference reward (gamma 0.5) | REINFORCE · threshold learning | learning | Improved |
Closest papers by meaning
- STARC: A General Framework For Quantifying Differences Between Reward Functions (ICLR 2024 · similarity 0.86)
- Flexible inference for animal learning rules using neural networks (NeurIPS 2025 · similarity 0.85)
- Inverse Reinforcement Learning with Switching Rewards and History Dependency for Characterizing Animal Behaviors (ICML 2025 · similarity 0.84)
- A Unifying Normative Framework of Decision Confidence (NeurIPS 2024 · similarity 0.84)
- Bayesian Exploration Networks (ICML 2024 · similarity 0.84)
- Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences (ICML 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.
