mlsanityData to 7 Oct 2026

Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing

arXiv 2602.19805 ↗First posted 23 Feb 2026cs.LG cs.AIcited by 0

On the map: State-space sequence models (S4, Mamba) → Core SSM architectures for language

also in 1 more
Abstract (arXiv)

Mamba-based models have drawn much attention in offline RL. However, their selective mechanism often detrimental when key steps in RL sequences are omitted. To address these issues, we propose a simple yet effective structure, called Decision MetaMamba (DMM), which replaces Mamba's token mixer with a dense layer-based sequence mixer and modifies positional structure to preserve local information. By performing sequence mixing that considers all channels simultaneously before Mamba, DMM prevents information loss due to selective scanning and residual gating. Extensive experiments demonstrate that our DMM delivers the state-of-the-art performance across diverse RL tasks. Furthermore, DMM achieves these results with a compact parameter footprint, demonstrating strong potential for real-world applications.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Placed in Core SSM architectures for language, one of 10 directions in State-space sequence models (S4, Mamba). Builds on 47 of its 51 references that are in the map. First posted on arXiv 23 Feb 2026.

Builds on

47 of 51 references.

Closest ancestors · 3

Same direction, newest first

  1. 2024Can Mamba Learn How to Learn? A Comparative Study on In-Context Learning Tasks6 Feb
  2. 2023Mamba: Linear-Time Sequence Modeling with Selective State Spaces1 Dec
  3. 2021Efficiently Modeling Long Sequences with Structured State Spaces31 Oct

Other references · 44

  1. 2017Attention Is All You Needcited by 59,932
  2. 2020Denoising Diffusion Probabilistic Modelscited by 20,851
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2016Layer Normalizationcited by 5,579
  5. 2020Longformer: The Long-Document Transformercited by 3,362
  6. 2023Diffusion Policy: Visuomotor Policy Learning via Action Diffusioncited by 2,730
  7. 2020Offline Reinforcement Learning: Tutorial, Review, and Perspectives on Open Problemscited by 1,873
  8. 2020Conformer: Convolution-augmented Transformer for Speech Recognitioncited by 1,838
  9. 2020Conservative Q-Learning for Offline Reinforcement Learningcited by 1,777
  10. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,528
  11. 2020D4RL: Datasets for Deep Data-Driven Reinforcement Learningcited by 1,406
  12. 2021Offline Reinforcement Learning with Implicit Q-Learningcited by 1,245
32 more
  1. 2018Off-Policy Deep Reinforcement Learning without Explorationcited by 1,227
  2. 2024Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Modelcited by 1,051
  3. 2024VMamba: Visual State Space Modelcited by 955
  4. 2021A Minimalist Approach to Offline Reinforcement Learningcited by 882
  5. 2016Language Modeling with Gated Convolutional Networkscited by 688
  6. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  7. 2021Combining Recurrent, Convolutional, and Continuous-time Models with Linear State-Space Layerscited by 607
  8. 2020HiPPO: Recurrent Memory with Optimal Polynomial Projectionscited by 600
  9. 2019Relay Policy Learning: Solving Long-Horizon Tasks via Imitation and Reinforcement Learningcited by 380
  10. 2020ReZero is All You Need: Fast Convergence at Large Depthcited by 260
  11. 2022Multi-Game Decision Transformerscited by 212
  12. 2021RvS: What is Essential for Offline RL via Supervised Learning?cited by 184
  13. 2024MambaOut: Do We Really Need Mamba for Vision?cited by 142
  14. 2024Graph-Mamba: Towards Long-Range Graph Sequence Modeling with Selective State Spacescited by 132
  15. 2024Is Mamba Effective for Time Series Forecasting?cited by 110
  16. 2021Beyond Self-attention: External Attention using Two Linear Layers for Visual Taskscited by 109
  17. 2024Caduceus: Bi-Directional Equivariant Long-Range DNA Sequence Modelingcited by 108
  18. 2021Generalized Decision Transformer for Offline Hindsight Information Matchingcited by 105
  19. 2022Q-learning Decision Transformer: Leveraging Dynamic Programming for Conditional Sequence Modelling in Offline RLcited by 103
  20. 2024SiMBA: Simplified Mamba-Based Architecture for Vision and Multivariate Time seriescited by 81
  21. 2023Elastic Decision Transformercited by 66
  22. 2021StARformer: Transformer with State-Action-Reward Representations for Visual Reinforcement Learningcited by 27
  23. 2021Koopman Q-learning: Offline Reinforcement Learning via Symmetries of Dynamicscited by 27
  24. 2023Decision S4: Efficient Sequence-Based RL via State Spaces Layerscited by 26
  25. 2023Decision ConvFormer: Local Filtering in MetaFormer is Sufficient for Decision Makingcited by 26
  26. 2023Critic-Guided Decision Transformer for Offline Reinforcement Learningcited by 25
  27. 2024Reinformer: Max-Return Sequence Modeling for Offline RLcited by 25
  28. 2024Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spacescited by 23
  29. 2023Waypoint Transformer: Reinforcement Learning via Supervised Learning with Intermediate Targetscited by 22
  30. 2024Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modelingcited by 18
  31. 2024Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RLcited by 15
  32. 2023Rethinking Decision Transformer via Hierarchical Reinforcement Learningcited by 14

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2024Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing
  2. 2024Hydra: Bidirectional State Space Models Through Generalized Matrix Mixers
  3. 2025PerfMamba: Performance Analysis and Pruning of Selective State Space Models
  4. 2024Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning
  5. 2024Is Mamba Compatible with Trajectory Optimization in Offline Reinforcement Learning?
  6. 2026InfoMamba: An Attention-Free Hybrid Mamba-Transformer Model
  7. 2025Regularity and Stability Properties of Selective SSMs with Discontinuous Gating
  8. 2026Bilinear Input Modulation for Mamba: Koopman Bilinear Forms for Memory Retention and Multiplicative Computation