探索利用论文趋势 2023–2026

Bandit 在线学习

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 235 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

探索利用论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202318919147
202430625263
2025201021354
2026252319471

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

全部探索利用论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 235 篇，第 4 / 5 页

  1. ICML 2024Random Latent Exploration for Deep Reinforcement Learning
  2. ICML 2024ReconBoost: Boosting Can Achieve Modality Reconcilement
  3. ICML 2024Safe and Robust Subgame Exploitation in Imperfect Information Games
  4. ICML 2024Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants
  5. ICML 2024Scalable Online Exploration via Coverability
  6. ICML 2024Stochastic Bandits with ReLU Neural Networks
  7. ICML 2024Straight-Through Meets Sparse Recovery: the Support Exploration Algorithm
  8. ICML 2024Testing the Feasibility of Linear Programs with Bandit Feedback
  9. NeurIPS 2024Bandits with Preference Feedback: A Stackelberg Game Perspective
  10. NeurIPS 2024Beyond Optimism: Exploration With Partially Observable Rewards
  11. NeurIPS 2024Code Repair with LLMs gives an Exploration-Exploitation Tradeoff
  12. NeurIPS 2024Effective Exploration Based on the Structural Information Principles
  13. NeurIPS 2024Exploration by Learning Diverse Skills through Successor State Representations
  14. NeurIPS 2024Exploration, Exploitation, and Engagement in Multi-Armed Bandits with Abandonment
  15. NeurIPS 2024First-Explore, then Exploit: Meta-Learning to Solve Hard Exploration-Exploitation Trade-Offs
  16. NeurIPS 2024Handling Learnwares from Heterogeneous Feature Spaces with Explicit Label Exploitation
  17. NeurIPS 2024Hierarchical Uncertainty Exploration via Feedforward Posterior Trees
  18. NeurIPS 2024How does Inverse RL Scale to Large State Spaces? A Provably Efficient Approach
  19. NeurIPS 2024Improved Analysis for Bandit Learning in Matching Markets
  20. NeurIPS 2024Improved Regret of Linear Ensemble Sampling
  21. NeurIPS 2024Local Anti-Concentration Class: Logarithmic Regret for Greedy Linear Contextual Bandit
  22. NeurIPS 2024Nearly Minimax Optimal Regret for Multinomial Logistic Bandit
  23. NeurIPS 2024NeoRL: Efficient Exploration for Nonepisodic RL
  24. NeurIPS 2024No-Regret Bandit Exploration based on Soft Tree Ensemble Model
  25. NeurIPS 2024Offline Oracle-Efficient Learning for Contextual MDPs via Layerwise Exploration-Exploitation Tradeoff
  26. NeurIPS 2024Online Learning of Delayed Choices
  27. NeurIPS 2024Online Non-convex Learning in Dynamic Environments
  28. NeurIPS 2024Optimal Clustering with Bandit Feedback
  29. NeurIPS 2024Optimizing the coalition gain in Online Auctions with Greedy Structured Bandits
  30. NeurIPS 2024Preference-based Pure Exploration
  31. NeurIPS 2024PRODuctive bandits: Importance Weighting No More
  32. NeurIPS 2024Progressive Exploration-Conformal Learning for Sparsely Annotated Object Detection in Aerial Images
  33. NeurIPS 2024Provably Efficient Interactive-Grounded Learning with Personalized Reward
  34. NeurIPS 2024Query-Efficient Correlation Clustering with Noisy Oracle
  35. NeurIPS 2024Randomized Exploration for Reinforcement Learning with Multinomial Logistic Function Approximation
  36. NeurIPS 2024Rethinking Exploration in Reinforcement Learning with Effective Metric-Based Exploration Bonus
  37. NeurIPS 2024Self-Guiding Exploration for Combinatorial Problems
  38. NeurIPS 2024Small steps no more: Global convergence of stochastic gradient bandits for arbitrary learning rates
  39. CVPR 2023Exact-NeRF: An Exploration of a Precise Volumetric Parameterization for Neural Radiance Fields
  40. ICLR 2023Combinatorial Pure Exploration of Causal Bandits
  41. ICLR 2023Guiding Safe Exploration with Weakest Preconditions
  42. ICLR 2023Learning Achievement Structure for Structured Exploration in Domains with Sparse Reward
  43. ICLR 2023Optimistic Exploration with Learned Features Provably Solves Markov Decision Processes with Neural Dynamics
  44. ICLR 2023Pink Noise Is All You Need: Colored Noise Exploration in Deep Reinforcement Learning
  45. ICLR 2023Replicable Bandits
  46. ICLR 2023Revisiting Intrinsic Reward for Exploration in Procedurally Generated Environments
  47. ICLR 2023Safe Exploration Incurs Nearly No Additional Sample Complexity for Reward-Free RL
  48. ICLR 2023Which Layer is Learning Faster? A Systematic Exploration of Layer-wise Convergence Rate for Deep Neural Networks
  49. ICML 2023An Information-Theoretic Analysis of Nonstationary Bandit Learning
  50. ICML 2023Anti-Exploration by Random Network Distillation

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查探索利用在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "exploration-exploitation"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇探索利用论文？
共 235 篇，按年份分别是 2023 年 47 篇、2024 年 63 篇、2025 年 54 篇、2026 年 71 篇。
NeurIPS 2026 有多少篇探索利用论文？
NeurIPS 2026 有 25 篇探索利用论文，上一届是 20 篇。
ICLR 2026 有多少篇探索利用论文？
ICLR 2026 有 23 篇探索利用论文，上一届是 10 篇。
ICML 2026 有多少篇探索利用论文？
ICML 2026 有 19 篇探索利用论文，上一届是 21 篇。
CVPR 2026 有多少篇探索利用论文？
CVPR 2026 有 4 篇探索利用论文，上一届是 3 篇。
哪个会议的探索利用论文最多？
NeurIPS，2023–2026 年共 93 篇。

「推荐与广告」下的其他主题