mlsanityData to 7 Oct 2026

t-DGR: A Trajectory-Based Deep Generative Replay Method for Continual Learning in Decision Making

arXiv 2401.02576 ↗First posted 4 Jan 2024cs.LG cs.AI cs.NEcited by 9

Not on the map. Why?

Abstract (arXiv)

Deep generative replay has emerged as a promising approach for continual learning in decision-making tasks. This approach addresses the problem of catastrophic forgetting by leveraging the generation of trajectories from previously encountered tasks to augment the current dataset. However, existing deep generative replay methods for continual learning rely on autoregressive models, which suffer from compounding errors in the generated trajectories. In this paper, we propose a simple, scalable, and non-autoregressive method for continual learning in decision-making tasks using a generative model that generates task samples conditioned on the trajectory timestep. We evaluate our method on Continual World benchmarks and find that our approach achieves state-of-the-art performance on the average success rate metric among continual learning methods. Code is available at https://github.com/WilliamYue37/t-DGR.

Key facts. Cited by 9 papers in the map (data through 7 Oct 2026). Builds on 32 of its 42 references that are in the map. First posted on arXiv 4 Jan 2024.

Builds on

32 of 42 references.

References · 32

  1. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  2. 2015U-Net: Convolutional Networks for Biomedical Image Segmentationcited by 19,604
  3. 2021Diffusion Models Beat GANs on Image Synthesiscited by 8,185
  4. 2015Deep Unsupervised Learning using Nonequilibrium Thermodynamicscited by 7,005
  5. 2022Generative Adversarial Networkscited by 5,603
  6. 2016Overcoming catastrophic forgetting in neural networkscited by 4,718
  7. 2021Improved Denoising Diffusion Probabilistic Modelscited by 3,736
  8. 2016Improved Techniques for Training GANscited by 2,938
  9. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  10. 2017Improved Training of Wasserstein GANscited by 2,223
  11. 2018Spectral Normalization for Generative Adversarial Networkscited by 1,618
  12. 2016Generative Adversarial Imitation Learningcited by 1,576
20 more
  1. 2019Meta-World: A Benchmark and Evaluation for Multi-Task and Meta Reinforcement Learningcited by 1,168
  2. 2017Continual Learning with Deep Generative Replaycited by 1,152
  3. 2017Memory Aware Synapses: Learning what (not) to forgetcited by 1,094
  4. 2020Dark Experience for General Continual Learning: a Strong, Simple Baselinecited by 895
  5. 2017PackNet: Adding Multiple Tasks to a Single Network by Iterative Pruningcited by 882
  6. 2023A Comprehensive Survey of Continual Learning: Theory, Method and Applicationcited by 860
  7. 2017Lifelong Learning with Dynamically Expandable Networkscited by 689
  8. 2019Three scenarios for continual learningcited by 610
  9. 2019Gradient based sample selection for online continual learningcited by 568
  10. 2018Progress & Compress: A scalable framework for continual learningcited by 516
  11. 2017Variational Continual Learningcited by 335
  12. 2021Rainbow Memory: Continual Learning with a Memory of Diverse Samplescited by 273
  13. 2018Re-evaluating Continual Learning Scenarios: A Categorization and Case for Strong Baselinescited by 228
  14. 2019Uncertainty-based Continual Learning with Adaptive Regularizationcited by 144
  15. 2023Continual Diffusion: Continual Customization of Text-to-Image Diffusion with C-LoRAcited by 138
  16. 2021Continual World: A Robotic Benchmark For Continual Reinforcement Learningcited by 112
  17. 2020Continual Learning with Node-Importance based Adaptive Group Sparse Regularizationcited by 102
  18. 2021CRIL: Continual Robot Imitation Learning via Generative and Prediction Modelcited by 23
  19. 2023Continual Learning of Diffusion Models with Generative Distillationcited by 19
  20. 2023Exploring Continual Learning of Diffusion Modelscited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 4; 2025: 2; 2026: 3.

9 papers.

  1. 2025A Survey of Continual Reinforcement Learningcited by 16
  2. 2024Solving Continual Offline RL through Selective Weights Activation on Aligned Spacescited by 6
  3. 2024Stable Continual Reinforcement Learning via Diffusion-based Trajectory Replaycited by 6
  4. 2024Continual Diffuser (CoD): Mastering Continual Offline Reinforcement Learning with Experience Rehearsalcited by 2
  5. 2026World Action Models Enable Continual Imitation Learning with Recurrent Generative Replayscited by 2
  6. 2026Harness Continual Learning: Continual Adaptation Beyond Model Parameterscited by 2
  7. 2024Continual Task Learning through Adaptive Policy Self-Compositioncited by 1
  8. 2025Action-Adaptive Continual Learning: Enabling Policy Generalization under Dynamic Action Spacescited by 1
  9. 2026Fine-Tuning VLAs with Self-Demonstrated Generative Control for Multi-Task Manipulationcited by 0