公共政策分析论文趋势 2023–2026

主要结论

• 公共政策分析论文从 2023 年的 16 篇增长到 2026 年的 29 篇，三年间扩大到约 1.8 倍。
• NeurIPS 是发公共政策分析论文最多的会议，2023–2026 年共 45 篇，占四个会议总量的 54%。
• 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 6 篇增至 2026 年的 18 篇。
• 在「社会公益」的 5 个主题里，它的 2026 年论文数排第 2；同组增长最快的电网优化是 2.6 倍，公共政策分析是 1.8 倍。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026Co-Evolving Policy Distillation
• ICML 2026Partial Identification of Policy Values under Network Interference
• ICLR 2026Joint Selection for Large-Scale Pre-Training Data via Policy Gradient-based Mask Learning
• CVPR 2026Real-Time Long Horizon Air Quality Forecasting via Group-Relative Policy Optimization
• NeurIPS 2025Real-Time Hyper-Personalized Generative AI Should Be Regulated to Prevent the Rise of "Digital Heroin"
• ICML 2025Improving Value Estimation Critically Enhances Vanilla Policy Gradient
• CVPR 2025AffordDP: Generalizable Diffusion Policy with Transferable Affordance
• NeurIPS 2024SafeWorld: Geo-Diverse Safety Alignment
• ICML 2024Optimal Differentially Private Model Training with Public Data
• NeurIPS 2023Creating a Public Repository for Joining Private Data
• ICML 2023Exponential Smoothing for Off-Policy Learning
• ICLR 2023Linear Convergence of Natural Policy Gradient Methods with Log-Linear Policies
• NeurIPS 2026Distributionally-Robust Policy Learning from Observational Data
• ICML 2026Personalized Policy Learning through Discrete Experimentation
• NeurIPS 2025$\textit{Hyper-GoalNet}$: Goal-Conditioned Manipulation Policy Learning with HyperNetworks
• ICML 2025Theoretical guarantees on the best-of-n alignment policy
• NeurIPS 2024Improved off-policy training of diffusion samplers
• ICML 2024Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
• NeurIPS 2023Global Optimality and Finite Sample Analysis of Softmax Off-Policy Actor Critic under State Distribution Mismatch
• ICML 2023On Many-Actions Policy Gradient

全部公共政策分析论文

共 35 篇，第 1 / 1 页

1. ICML 2026Partial Identification of Policy Values under Network Interference
2. ICML 2026Personalized Policy Learning through Discrete Experimentation
3. ICML 2026Recurrent Structural Policy Gradient for Partially Observable Mean Field Games
4. ICML 2026Reusing Trajectories in Policy Gradients Enables Fast Convergence
5. ICML 2026Unlearning with Asymmetric Sources: Improved Unlearning-Utility Trade-off with Public Data
6. ICML 2025Convergence Analysis of Policy Gradient Methods with Dynamic Stochasticity
7. ICML 2025Distributed Differentially Private Data Analytics via Secure Sketching
8. ICML 2025Improving Value Estimation Critically Enhances Vanilla Policy Gradient
9. ICML 2025Return Capping: Sample Efficient CVaR Policy Gradient Optimisation
10. ICML 2025The Value of Prediction in Identifying the Worst-Off
11. ICML 2025Theoretical guarantees on the best-of-n alignment policy
12. ICML 2024ACE: Off-Policy Actor-Critic with Causality-Aware Entropy Regularization
13. ICML 2024Building Socially-Equitable Public Models
14. ICML 2024Fair Off-Policy Learning from Observational Data
15. ICML 2024Feasible Reachable Policy Iteration
16. ICML 2024GFlowNet Training by Policy Gradients
17. ICML 2024Learning Optimal Deterministic Policies with Stochastic Policy Gradients
18. ICML 2024Mollification Effects of Policy Gradient Methods
19. ICML 2024Offline-Boosted Actor-Critic: Adaptively Blending Optimal Historical Behaviors in Deep Off-Policy RL
20. ICML 2024On the Second-Order Convergence of Biased Policy Gradient Algorithms
21. ICML 2024Optimal Differentially Private Model Training with Public Data
22. ICML 2024Policy-conditioned Environment Models are More Generalizable
23. ICML 2024Position: Amazing Things Come From Having Many Good Models
24. ICML 2024Position: Considerations for Differentially Private Learning with Large-Scale Public Pretraining
25. ICML 2024ReLU to the Rescue: Improve Your On-Policy Actor-Critic with Positive Advantages
26. ICML 2024Seizing Serendipity: Exploiting the Value of Past Success in Off-Policy Actor-Critic
27. ICML 2024Stealthy Imitation: Reward-guided Environment-free Policy Stealing
28. ICML 2023Exponential Smoothing for Off-Policy Learning
29. ICML 2023Live in the Moment: Learning Dynamics Model Adapted to Evolving Policy
30. ICML 2023On Many-Actions Policy Gradient
31. ICML 2023Policy Contrastive Imitation Learning
32. ICML 2023Policy Gradient in Robust MDPs with Global Convergence Guarantee
33. ICML 2023PPG Reloaded: An Empirical Study on What Matters in Phasic Policy Gradient
34. ICML 2023Stochastic Policy Gradient Methods: Improved Sample Complexity for Fisher-non-degenerate Policies
35. ICML 2023The Optimal Approximation Factors in Misspecified Off-Policy Value Function Estimation

常见问题

2023–2026 年四大会议一共有多少篇公共政策分析论文？

共 84 篇，按年份分别是 2023 年 16 篇、2024 年 21 篇、2025 年 18 篇、2026 年 29 篇。

NeurIPS 2026 有多少篇公共政策分析论文？

NeurIPS 2026 有 22 篇公共政策分析论文，上一届是 11 篇。

ICLR 2026 有多少篇公共政策分析论文？

ICLR 2026 有 1 篇公共政策分析论文。

ICML 2026 有多少篇公共政策分析论文？

ICML 2026 有 5 篇公共政策分析论文，上一届是 6 篇。

CVPR 2026 有多少篇公共政策分析论文？

CVPR 2026 有 1 篇公共政策分析论文，上一届是 1 篇。

哪个会议的公共政策分析论文最多？

NeurIPS，2023–2026 年共 45 篇。