Decision Mamba Architectures

2024-05-13 · André Correia, Luís A. Alexandre

Recent advancements in imitation learning have been largely fueled by the integration of sequence models, which provide a structured flow of information to effectively mimic task behaviours. Currently, Decision Transformer (DT) and subsequently, the Hierarchical Decision Transformer (HDT), presented Transformer-based approaches to learn task policies. Recently, the Mamba architecture has shown to outperform Transformers across various task domains. In this work, we introduce two novel methods, Decision Mamba (DM) and Hierarchical Decision Mamba (HDM), aimed at enhancing the performance of the Transformer models. Through extensive experimentation across diverse environments such as OpenAI Gym and D4RL, leveraging varying demonstration data sets, we demonstrate the superiority of Mamba models over their Transformer counterparts in a majority of tasks. Results show that DM outperforms other methods in most settings. The code can be found at https://github.com/meowatthemoon/DecisionMamba.

📄 PDF Abstract BibTeX arXiv:2405.07943

Code (2)

meowatthemoon/decisionmamba 공식 구현 pytorch

meowatthemoon/hierarchicaldecisionmamba 공식 구현 pytorch

Tasks

D4RLImitation LearningMambaOpenAI Gym

Methods 이 논문이 사용한 방법론

Attention 설명 없음

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Multi-Head Attention 설명 없음

Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…

Position-Wise Feed-Forward Layer 설명 없음

Dropout Dropout is a regularization technique for neural networks that drops a unit (along with connections) at training time with a specified probability $p$ (a common value is…

Label Smoothing Label Smoothing is a regularization technique that introduces noise for the labels. This accounts for the fact that datasets may have mistakes in them, so maximizing the…

Residual Connection 설명 없음

Decision Mamba: Reinforcement Learning via Sequence Modeling with Selective State Spaces

2024-03-29 · Toshihiro Ota

Decision Transformer, a promising approach that applies Transformer architectures to reinforcement learning, relies on causal self-attention to model sequences of states, actions, and rewards. While this method has shown…

Decision Making Mamba reinforcement-learning Reinforcement Learning+1

RLBenchNet: The Right Network for the Right Reinforcement Learning Task

2025-05-21 · Ivan Smirnov, Shangding Gu

Reinforcement learning (RL) has seen significant advancements through the application of various neural network architectures. In this study, we systematically investigate the performance of several neural networks in RL…

continuous-control Continuous Control Mamba Reinforcement Learning (RL)

ms-Mamba: Multi-scale Mamba for Time-Series Forecasting

2025-04-10 · Yusuf Meric Karadag, Sinan Kalkan, Ipek Gursel Dino

The problem of Time-series Forecasting is generally addressed by recurrent, Transformer-based and the recently proposed Mamba-based architectures. However, existing architectures generally process their input at a single…

Mamba Time Series Time Series Forecasting

DYNAMAX: Dynamic computing for Transformers and Mamba based architectures

2025-04-29 · Miguel Nogales, Matteo Gambella, Manuel Roveri

Early exits (EEs) offer a promising approach to reducing computational costs and latency by dynamically terminating inference once a satisfactory prediction confidence on a data sample is achieved. Although many works in…

Mamba TriviaQA TruthfulQA

One Dimensional CNN ECG Mamba for Multilabel Abnormality Classification in 12 Lead ECG

2025-10-14 · Huawei Jiang, Husna Mutahira, Gan Huang, Mannan Saeed Muhammad arxiv

Accurate detection of cardiac abnormalities from electrocardiogram recordings is regarded as essential for clinical diagnostics and decision support. Traditional deep learning models such as residual networks and transfo…

ECG Classification