mlsanityData to 7 Oct 2026

Reinforced Continual Learning

arXiv 1805.12369 ↗First posted 31 May 2018cs.LG cs.CV stat.MLcited by 186

Not on the map. Why?

Abstract (arXiv)

Most artificial intelligence models have limiting ability to solve new tasks faster, without forgetting previously acquired knowledge. The recently emerging paradigm of continual learning aims to solve this issue, in which the model learns various tasks in a sequential fashion. In this work, a novel approach for continual learning is proposed, which searches for the best neural architecture for each coming task via sophisticatedly designed reinforcement learning strategies. We name it as Reinforced Continual Learning. Our method not only has good performance on preventing catastrophic forgetting but also fits new tasks well. The experiments on sequential classification tasks for variants of MNIST and CIFAR-100 datasets demonstrate that the proposed approach outperforms existing continual learning alternatives for deep networks.

Key facts. Cited by 186 papers in the map (data through 7 Oct 2026). First posted on arXiv 31 May 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 29; 2022: 38; 2023: 52; 2024: 35; 2025: 23; 2026: 9.

186 papers.

Sort:

By area:

  1. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  2. 2021Gradient Projection Memory for Continual Learningcited by 338
  3. 2023Class-Incremental Learning: A Surveycited by 209
  4. 2023Revisiting Class-Incremental Learning with Pre-Trained Models: Generalizability and Adaptivity are All You Needcited by 183
  5. 2022A Model or 603 Exemplars: Towards Memory-Efficient Class-Incremental Learningcited by 152
  6. 2021Online Coreset Selection for Rehearsal-based Continual Learningcited by 114
  7. 2024Mitigating Catastrophic Forgetting in Large Language Models with Self-Synthesized Rehearsalcited by 114
  8. 2022Few-Shot Class-Incremental Learning by Sampling Multi-Phase Taskscited by 87
  9. 2022TRGP: Trust Region Gradient Projection for Continual Learningcited by 79
  10. 2023Learning without Forgetting for Vision-Language Modelscited by 79
  11. 2022A Theoretical Study on Solving Continual Learningcited by 78
  12. 2021Flattening Sharpness for Dynamic Gradient Projection Memory Benefits Continual Learningcited by 71
38 more
  1. 2023RMM: Reinforced Memory Management for Class-Incremental Learningcited by 66
  2. 2021Wide Neural Networks Forget Less Catastrophicallycited by 64
  3. 2023TARGET: Federated Class-Continual Learning via Exemplar-Free Distillationcited by 64
  4. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
  5. 2021Few-Shot Lifelong Learningcited by 58
  6. 2021Recent Advances of Continual Learning in Computer Vision: An Overviewcited by 55
  7. 2022An Efficient Domain-Incremental Learning Approach to Drive in All Weather Conditionscited by 54
  8. 2021Model Zoo: A Growing "Brain" That Learns Continuallycited by 53
  9. 2021Efficient Feature Transformations for Discriminative and Generative Continual Learningcited by 50
  10. 2023Class-Incremental Exemplar Compression for Class-Incremental Learningcited by 50
  11. 2021Firefly Neural Architecture Descent: a General Approach for Growing Neural Networkscited by 48
  12. 2022Architecture Matters in Continual Learningcited by 46
  13. 2022Continual Normalization: Rethinking Batch Normalization for Online Continual Learningcited by 40
  14. 2021Co-Transport for Class-Incremental Learningcited by 38
  15. 2022On the Soft-Subnetwork for Few-shot Class Incremental Learningcited by 37
  16. 2023Online Hyperparameter Optimization for Class-Incremental Learningcited by 36
  17. 2024Scaling Laws for Forgetting When Fine-Tuning Large Language Modelscited by 36
  18. 2021Wanderlust: Online Continual Object Detection in the Real Worldcited by 34
  19. 2022Grow and Merge: A Unified Framework for Continuous Categories Discoverycited by 33
  20. 2023Continual Learning with Scaled Gradient Projectioncited by 33
  21. 2022Mining Unseen Classes via Regional Objectness: A Simple Baseline for Incremental Segmentationcited by 28
  22. 2022Building a Subspace of Policies for Scalable Continual Learningcited by 28
  23. 2023Artificial intelligence to advance Earth observation: : A review of models, recent trends, and pathways forwardcited by 28
  24. 2023Learnability and Algorithm for Continual Learningcited by 28
  25. 2021Learngene: From Open-World to Your Learning Taskcited by 27
  26. 2022Learning Bayesian Sparse Networks with Full Experience Replay for Continual Learningcited by 27
  27. 2021Block Contextual MDPs for Continual Learningcited by 25
  28. 2022Reinforced Continual Learning for Graphscited by 24
  29. 2023Fixed Design Analysis of Regularization-Based Continual Learningcited by 24
  30. 2023Catastrophic Forgetting in Deep Learning: A Comprehensive Taxonomycited by 24
  31. 2022Towards Exemplar-Free Continual Learning in Vision Transformers: an Account of Attention, Functional and Weight Regularizationcited by 23
  32. 2022You Only Live Once: Single-Life Reinforcement Learningcited by 23
  33. 2023Continual Face Forgery Detection via Historical Distribution Preservingcited by 23
  34. 2024Unleashing the Power of Continual Learning on Non-Centralized Devices: A Surveycited by 23
  35. 2022Continual Learning Based on OOD Detection and Task Maskingcited by 21
  36. 2023Practical PCG Through Large Language Modelscited by 21
  37. 2022Do Pre-trained Models Benefit Equally in Continual Learning?cited by 20
  38. 2022Learning Incrementally to Segment Multiple Organs in a CT Imagecited by 19

50 most cited of 186 All 186 (JSON)