mlsanityData to 7 Oct 2026

Decision transformers and sequence modeling

205 papers0 this weekMedium confidence in this grouping: mostly one topic, with blurry edgesMedium confidence in this grouping: mostly one topic, with blurry edges · About

Keywords: decision, transformer, offline, decision transformer, reinforcement

Key facts. Decision transformers and sequence modeling: 205 papers on arXiv since 2019 (data through 7 Oct 2026). 108 of its 205 mapped papers (53%) cite “Decision Transformer: Reinforcement Learning via Sequence Modeling” (2021, arXiv 2106.01345). 64 of its 205 mapped papers (31%) cite “Offline Reinforcement Learning as One Big Sequence Modeling Problem” (2021, arXiv 2106.02039). 5 new papers 17 Sep–7 Oct.

What’s new

17 Sep – 7 Oct 2026

5 new papers, 17 Sep – 7 Oct; 0 this week.

  1. Earlier · 5
  2. Decision Titan: Test-Time Training for Long-Term Memory in Offline Reinforcement Learning
  3. Q-learning Penalized Transformer for Safe Offline Reinforcement Learning also fits: Safe offline RL
  4. Trust Guided Decision Transformer
  5. Offline Reinforcement Learning for Distribution-Grid Protection also fits: Offline multi-agent RL
  6. Learning Control Policies from Heterogeneous Multi-Horizon Time Series in Battery Energy Management Systems

Foundations

Most cited by papers here

  1. Decision Transformer: Reinforcement Learning via Sequence Modeling2021cited by 108 here
  2. Offline Reinforcement Learning as One Big Sequence Modeling Problem2021cited by 64 here
  3. Online Decision Transformer2022cited by 34 here
  4. Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RL2022cited by 32 here
  5. Multi-Game Decision Transformers2022cited by 31 here

Lineage

The papers this direction builds on, oldest first.

Each paper on the line cites the one before.

  1. 2019An Optimistic Perspective on Offline Reinforcement Learningcited by 30 here
  2. 2019Behavior Regularized Offline Reinforcement Learningcited by 29 here
  3. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 78 here
  4. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 84 here
  5. 2020MOReL : Model-Based Offline Reinforcement Learningcited by 23 here
  6. 2020MOPO: Model-based Offline Policy Optimizationcited by 21 here
  7. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 108 here
  8. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 46 here
  9. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 30 here
  10. 2022You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environmentscited by 15 here
  11. 2022When does return-conditioned supervised learning work for offline reinforcement learning?cited by 16 here
13 more it builds on, not in this chain
  1. 2019Learning to Reach Goals via Iterated Supervised Learningcited by 14 here
  2. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 87 here
  3. 2020Offline Meta-Reinforcement Learning with Advantage Weightingcited by 21 here
  4. 2021COMBO: Conservative Offline Model-Based Policy Optimizationcited by 18 here
  5. 2021Offline Reinforcement Learning with Fisher Divergence Critic Regularizationcited by 15 here
  6. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 64 here
  7. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 56 here
  8. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 25 here
  9. 2022Online Decision Transformercited by 34 here
  10. 2022Multi-Game Decision Transformerscited by 31 here
  11. 2022Prompting Decision Transformer for Few-Shot Policy Generalizationcited by 28 here
  12. 2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RLcited by 32 here
  13. 2023Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Makingcited by 15 here

The 24 most cited of 317.

Browse

30 of 205, ranked 6–35

  1. 6Generalized Decision Transformer for Offline Hindsight Information Matching202130
  2. 7Prompting Decision Transformer for Few-Shot Policy Generalization202228
  3. 8Offline Meta-Reinforcement Learning with Advantage Weighting202021
  4. 9Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Making202315
  5. 10You Can't Count on Luck: Why Decision Transformers and RvS Fail in Stochastic Environments202215
  6. 11Future-conditioned Unsupervised Pretraining for Decision Transformer202313
  7. 12Can Wikipedia Help Offline Reinforcement Learning?202213
  8. 13Critic-Guided Decision Transformer for Offline Reinforcement Learning202312
  9. 14FOCAL: Efficient Fully-Offline Meta-Reinforcement Learning via Distance Metric Learning and Behavior Regularization202012
  10. 15Dichotomy of Control: Separating What You Can Control from What You Cannot202211
All 30
  1. 16Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targets202310
  2. 17Reinformer: Max-Return Sequence Modeling for Offline RL20249
  3. 18Hyper-Decision Transformer for Efficient Online Policy Adaptation20239
  4. 19Decision S4: Efficient Sequence-Based RL via State Spaces Layers20239
  5. 20Q-value Regularized Transformer for Offline Reinforcement Learning20248
  6. 21Graph Decision Transformer20238
  7. 22Robust Task Representations for Offline Meta-Reinforcement Learning via Contrastive Learning20228
  8. 23Offline Meta-Reinforcement Learning with Online Self-Supervision20218
  9. 24When should we prefer Decision Transformers for Offline Reinforcement Learning?20237
  10. 25Rethinking Decision Transformer via Hierarchical Reinforcement Learning20237
  11. 26Bootstrapped Transformer for Offline Reinforcement Learning20227
  12. 27Unleashing the Power of Pre-trained Language Models for Offline Reinforcement Learning20236
  13. 28Hierarchical Decision Transformer20226
  14. 29Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces20245
  15. 30Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL20245
  16. 31Offline Meta Reinforcement Learning with In-Distribution Online Adaptation20235
  17. 32ACT: Empowering Decision Transformer with Dynamic Programming via Advantage Conditioning20235
  18. 33Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functions20235
  19. 34Transformers as Decision Makers: Provable In-Context Reinforcement Learning via Supervised Pretraining20235
  20. 35Context Shift Reduction for Offline Meta-Reinforcement Learning20235