paper-with-me

홈 › Papers

Decision Mamba: Reinforcement Learning via Hybrid Selective Sequence Modeling

2024-05-31 · Sili Huang, Jifeng Hu, Zhejian Yang, Liwei Yang, Tao Luo, Hechang Chen, Lichao Sun, Bo Yang

Recent works have shown the remarkable superiority of transformer models in reinforcement learning (RL), where the decision-making problem is formulated as sequential generation. Transformer-based agents could emerge with self-improvement in online environments by providing task contexts, such as multiple trajectories, called in-context RL. However, due to the quadratic computation complexity of attention in transformers, current in-context RL methods suffer from huge computational costs as the task horizon increases. In contrast, the Mamba model is renowned for its efficient ability to process long-term dependencies, which provides an opportunity for in-context RL to solve tasks that require long-term memory. To this end, we first implement Decision Mamba (DM) by replacing the backbone of Decision Transformer (DT). Then, we propose a Decision Mamba-Hybrid (DM-H) with the merits of transformers and Mamba in high-quality prediction and long-term memory. Specifically, DM-H first generates high-value sub-goals from long-term memory through the Mamba model. Then, we use sub-goals to prompt the transformer, establishing high-quality predictions. Experimental results demonstrate that DM-H achieves state-of-the-art in long and short-term tasks, such as D4RL, Grid World, and Tmaze benchmarks. Regarding efficiency, the online testing of DM-H in the long-term task is 28$\times$ times faster than the transformer-based baselines.

📄 PDF Abstract BibTeX arXiv:2406.00079

Code (0)

등록된 구현이 없습니다.

Tasks

D4RLMambareinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Attention 설명 없음
Residual Connection 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
BPE Byte Pair Encoding, or BPE, is a subword segmentation algorithm that encodes rare and unknown words as sequences of subword units. The intuition is that various word…
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…
Adam 설명 없음
Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.

Similar Papers 제목 키워드 기반

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 MakingMambareinforcement-learningReinforcement Learning+1

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

2026-02-23 · Wall Kim, Chaeyoung Song, Hanul Kim 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 stru…

Offline RL

MambaMIM: Pre-training Mamba with State Space Token Interpolation and its Application to Medical Image Segmentation

2024-08-15 · Fenghe Tang, Bingkun Nian, Yingtai Li, Zihang Jiang 외

Recently, the state space model Mamba has demonstrated efficient long-sequence modeling capabilities, particularly for addressing long-sequence visual tasks in 3D medical imaging. However, existing generative self-superv…

Image SegmentationMambaMedical Image SegmentationRepresentation Learning+3

Integrating Multi-Modal Input Token Mixer Into Mamba-Based Decision Models: Decision MetaMamba

2024-08-20 · Wall Kim

Sequence modeling with State Space models (SSMs) has demonstrated performance surpassing that of Transformers in various tasks, raising expectations for their potential to outperform the Decision Transformer and its enha…

MambaOffline RLReinforcement Learning (RL)State Space Models

Phoneme- vs. Character-Level Targets and Selective State-Space Models for Intracortical Brain-to-Text

2026-07-29 · Lucas Zamora Vera, Jose A. Gonzalez-Lopez arxiv

State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain underexplored: whether selective state-space models (Mamba) improve on rec…