通用机器学习 · reinforcement learning论文趋势 2023–2026

通用机器学习：reinforcement_learning

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,676 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

通用机器学习 · reinforcement learning论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
202314666723287
2024101216824403
2025108230712411
202611333511314575

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

全部通用机器学习 · reinforcement learning论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,676 篇，第 5 / 34 页

  1. ICLR 2026Octax: Accelerated CHIP-8 Arcade Environments for Reinforcement Learning in JAX
  2. ICLR 2026Off-Policy Evaluation for Ranking Policies under Deterministic Logging Policies
  3. ICLR 2026Off-Policy Safe Reinforcement Learning with Cost-Constrained Optimistic Exploration
  4. ICLR 2026Offline Preference-Based Value Optimization
  5. ICLR 2026Offline Reinforcement Learning with Adaptive Feature Fusion
  6. ICLR 2026On Discovering Algorithms for Adversarial Imitation Learning
  7. ICLR 2026On Entropy Control in LLM-RL Algorithms
  8. ICLR 2026On the Computational Limits of AI4S-RL : A Unified $\varepsilon$-$N$ Analysis
  9. ICLR 2026On the Design of KL-Regularized Policy Gradient Algorithms for LLM Reasoning
  10. ICLR 2026On the Direction of RLVR Updates for LLM Reasoning: Identification and Exploitation
  11. ICLR 2026On the Generalization of SFT: A Reinforcement Learning Perspective with Reward Rectification
  12. ICLR 2026On the Tension Between Optimality and Adversarial Robustness in Policy Optimization
  13. ICLR 2026One Model for All Tasks: Leveraging Efficient World Models in Multi-Task Planning
  14. ICLR 2026One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
  15. ICLR 2026OPPO: Accelerating PPO-based RLHF via Pipeline Overlap
  16. ICLR 2026OPRIDE: Efficient Offline Preference-based Reinforcement Learning via In-Dataset Exploration
  17. ICLR 2026Optimal Robust Subsidy Policies for Irrational Agent in Principal-Agent MDPs
  18. ICLR 2026Optimistic Task Inference for Behavior Foundation Models
  19. ICLR 2026Parameter-Efficient Reinforcement Learning using Prefix Optimization
  20. ICLR 2026Partially Equivariant Reinforcement Learning in Symmetry-Breaking Environments
  21. ICLR 2026Peak-Return Greedy Slicing: Subtrajectory Selection for Transformer-based Offline RL
  22. ICLR 2026Peng's Q($\lambda$) for Conservative Value Estimation in Offline Reinforcement Learning
  23. ICLR 2026Policy Likelihood-based Query Sampling and Critic-Exploited Reset for Efficient Preference-based Reinforcement Learning
  24. ICLR 2026Policy Newton Algorithm in Reproducing Kernel Hilbert Space
  25. ICLR 2026PolicyFlow: Policy Optimization with Continuous Normalizing Flow in Reinforcement Learning
  26. ICLR 2026Polychromic Objectives for Reinforcement Learning
  27. ICLR 2026Post-training Large Language Models for Diverse High-Quality Responses
  28. ICLR 2026Potentially Optimal Joint Actions Recognition for Cooperative Multi-Agent Reinforcement Learning
  29. ICLR 2026Predictive CVaR Q-learning
  30. ICLR 2026Preference-based Policy Optimization from Sparse-reward Offline Dataset
  31. ICLR 2026Primal-Dual Policy Optimization for Adversarial Linear CMDPs
  32. ICLR 2026Principled Fast and Meta Knowledge Learners for Continual Reinforcement Learning
  33. ICLR 2026Probing in the Dark: State Entropy Maximization for POMDPs
  34. ICLR 2026Probing to Refine: Reinforcement Distillation of LLM Reasoners via Explanatory Inversion
  35. ICLR 2026Prompt Curriculum Learning for Efficient LLM Post-Training
  36. ICLR 2026Q-Learning with Adjoint Matching
  37. ICLR 2026Q-Learning with Fine-Grained Gap-Dependent Regret
  38. ICLR 2026Q-learning with Posterior Sampling
  39. ICLR 2026Q-RAG: Long Context Multi‑Step Retrieval via Value‑Based Embedder Training
  40. ICLR 2026Quantile Advantage Estimation for Entropy-Safe Reasoning
  41. ICLR 2026Queue Length Regret Bounds for Contextual Queueing Bandits
  42. ICLR 2026R2-Dreamer: Redundancy-Reduced World Models without Decoders or Augmentation
  43. ICLR 2026RD-HRL: Generating Reliable Sub-Goals for Long-Horizon Sparse-Reward Tasks
  44. ICLR 2026REA-RL: Reflection-Aware Online Reinforcement Learning for Efficient Reasoning
  45. ICLR 2026Reasoning as Representation: Rethinking Visual Reinforcement Learning in Image Quality Assessment
  46. ICLR 2026Recurrent Action Transformer with Memory
  47. ICLR 2026Reevaluating Policy Gradient Methods for Imperfect-Information Games
  48. ICLR 2026Reference Guided Skill Discovery
  49. ICLR 2026Refining Hybrid Genetic Search for CVRP via Reinforcement Learning-Finetuned LLM
  50. ICLR 2026ReFORM: Reflected Flows for On-support Offline RL via Noise Manipulation

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 查通用机器学习 · reinforcement learning在 ICLR 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": "gml-reinforcement-learning"}

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通用机器学习 · reinforcement learning论文？
共 1,676 篇，按年份分别是 2023 年 287 篇、2024 年 403 篇、2025 年 411 篇、2026 年 575 篇。
NeurIPS 2026 有多少篇通用机器学习 · reinforcement learning论文？
NeurIPS 2026 有 113 篇通用机器学习 · reinforcement learning论文，上一届是 108 篇。
ICLR 2026 有多少篇通用机器学习 · reinforcement learning论文？
ICLR 2026 有 335 篇通用机器学习 · reinforcement learning论文，上一届是 230 篇。
ICML 2026 有多少篇通用机器学习 · reinforcement learning论文？
ICML 2026 有 113 篇通用机器学习 · reinforcement learning论文，上一届是 71 篇。
CVPR 2026 有多少篇通用机器学习 · reinforcement learning论文？
CVPR 2026 有 14 篇通用机器学习 · reinforcement learning论文，上一届是 2 篇。
哪个会议的通用机器学习 · reinforcement learning论文最多？
ICLR，2023–2026 年共 847 篇。

「通用机器学习」下的其他主题