Research map / Reinforcement learning / Policy gradient and actor-critic
Conformal Policy Control
Drew Prinster, Clara Fannjiang, Ji Won Park, Kyunghyun Cho, Anqi Liu, Suchi Saria, Samuel Don Stanton
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 |
|---|---|---|---|
| apply generalized CRC (gCRC) instead of CRC on monotonized losses or LTT | FDR control on non-monotonic loss · MedLFQA | recall | Improved |
| add CPC risk control to active-learning acquisition policy | GP acquisition by exponential tilting · Robot Arm, Airfoil, MEPS active learning | test MSE | Improved |
| add CPC risk control to DPO sequence optimization | Pythia 14M policy · Ehrlich Ehr(32,32)-4-4-4 | infeasibility rate: over 80% -> controlled at alpha | Improved |
| use moderate risk control alpha > 0.6 versus none (ablation) | CPC · Ehrlich sequence optimization | objective value | Improved |
| add CPC to Constrained Bayesian Optimization across temperatures 2.0, 1.0, 0.1 | CBO baseline · synthetic constrained BO | violation rate: target alpha=0.4 | Improved |
Closest papers by meaning
- Sampling-Based Safe Reinforcement Learning (NeurIPS 2026 · similarity 0.86)
- Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis (AAAI 2024 · similarity 0.86)
- Enhancing Safety in Reinforcement Learning with Human Feedback via Rectified Policy Optimization (NeurIPS 2025 · similarity 0.85)
- Conformal Arbitrage: Risk-Controlled Balancing of Competing Objectives in Language Models (NeurIPS 2025 · similarity 0.85)
- Enhancing Efficiency of Safe Reinforcement Learning via Sample Manipulation (NeurIPS 2024 · similarity 0.85)
- Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration (AAAI 2024 · similarity 0.85)
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.
