Imagen de Portada

Mamba as Decision Maker: Exploring Multi-scale Sequence Modeling in Offline Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Cao, Jiahang, Zhang, Qiang, Wang, Ziqing, Sun, Jingkai, Wang, Jiaxu, Cheng, Hao, Shao, Yecheng, Zhao, Wen, Han, Gang, Guo, Yijie, Xu, Renjing
Formato:	Preprint
Publicado:	2024
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

Reinforcement Learning with Generalizable Gaussian Splatting
por: Wang, Jiaxu, et al.
Publicado: (2024)

ES-Parkour: Advanced Robot Parkour with Bio-inspired Event Camera and Spiking Neural Network
por: Zhang, Qiang, et al.
Publicado: (2025)

Mamba Policy: Towards Efficient 3D Diffusion Policy with Hybrid Selective State Models
por: Cao, Jiahang, et al.
Publicado: (2024)

LiPS: Large-Scale Humanoid Robot Reinforcement Learning with Parallel-Series Structures
por: Zhang, Qiang, et al.
Publicado: (2025)

Distillation-PPO: A Novel Two-Stage Reinforcement Learning Framework for Humanoid Robot Perceptive Locomotion
por: Zhang, Qiang, et al.
Publicado: (2025)

Event Masked Autoencoder: Point-wise Action Recognition with Event-Based Cameras
por: Sun, Jingkai, et al.
Publicado: (2025)

Trinity: A Modular Humanoid Robot AI System
por: Sun, Jingkai, et al.
Publicado: (2025)

DPL: Depth-only Perceptive Humanoid Locomotion via Realistic Depth Synthesis and Cross-Attention Terrain Reconstruction
por: Sun, Jingkai, et al.
Publicado: (2025)

Modality-Composable Diffusion Policy via Inference-Time Distribution-level Composition
por: Cao, Jiahang, et al.
Publicado: (2025)

Spiking Diffusion Models
por: Cao, Jiahang, et al.
Publicado: (2024)

Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Networks
por: Wang, Ziqing, et al.
Publicado: (2023)

Occupancy World Model for Robots
por: Zhang, Zhang, et al.
Publicado: (2025)

MoSA: Motion-constrained Stress Adaptation for Mitigating Real-to-Sim Gap in Continuum Dynamics via Learning Residual Anisotropy
por: Wang, Jiaxu, et al.
Publicado: (2026)

Spiking Neural Network as Adaptive Event Stream Slicer
por: Cao, Jiahang, et al.
Publicado: (2024)

HumanoidPano: Hybrid Spherical Panoramic-LiDAR Cross-Modal Perception for Humanoid Robots
por: Zhang, Qiang, et al.
Publicado: (2025)

Adaptive Calibration: A Unified Conversion Framework of Spiking Neural Network
por: Wang, Ziqing, et al.
Publicado: (2024)

E2H: A Two-Stage Non-Invasive Neural Signal Driven Humanoid Robotic Whole-Body Control Framework
por: Duan, Yiqun, et al.
Publicado: (2024)

Fully Spiking Neural Network for Legged Robots
por: Jiang, Xiaoyang, et al.
Publicado: (2023)

Gaining the Sparse Rewards by Exploring Lottery Tickets in Spiking Neural Network
por: Cheng, Hao, et al.
Publicado: (2023)

Robust SG-NeRF: Robust Scene Graph Aided Neural Surface Reconstruction
por: Gu, Yi, et al.
Publicado: (2024)

Chasing Day and Night: Towards Robust and Efficient All-Day Object Detection Guided by an Event Camera
por: Cao, Jiahang, et al.
Publicado: (2023)

DEGS: Deformable Event-based 3D Gaussian Splatting from RGB and Event Stream
por: He, Junhao, et al.
Publicado: (2025)

Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learning
por: Wang, Jiaxu, et al.
Publicado: (2024)

Spiking Wavelet Transformer
por: Fang, Yuetong, et al.
Publicado: (2024)

Sparse View Distractor-Free Gaussian Splatting
por: Gu, Yi, et al.
Publicado: (2026)

DEL: Discrete Element Learner for Learning 3D Particle Dynamics with Neural Rendering
por: Wang, Jiaxu, et al.
Publicado: (2024)

EvGGS: A Collaborative Learning Framework for Event-based Generalizable Gaussian Splatting
por: Wang, Jiaxu, et al.
Publicado: (2024)

Compose Your Policies! Improving Diffusion-based or Flow-based Robot Policies via Test-time Distribution-level Composition
por: Cao, Jiahang, et al.
Publicado: (2025)

MeshMimic: Geometry-Aware Humanoid Motion Learning through 3D Scene Reconstruction
por: Zhang, Qiang, et al.
Publicado: (2026)

HarmoDT: Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
por: Hu, Shengchao, et al.
Publicado: (2024)

Whole-body Humanoid Robot Locomotion with Human Reference
por: Zhang, Qiang, et al.
Publicado: (2024)

Exploring Typographic Visual Prompts Injection Threats in Cross-Modality Generation Models
por: Cheng, Hao, et al.
Publicado: (2025)

DecisionFlow: Advancing Large Language Model as Principled Decision Maker
por: Chen, Xiusi, et al.
Publicado: (2025)

Task-Aware Harmony Multi-Task Decision Transformer for Offline Reinforcement Learning
por: Fan, Ziqing, et al.
Publicado: (2024)

Learning Robust Generalizable Radiance Field with Visibility and Feature Augmented Point Representation
por: Wang, Jiaxu, et al.
Publicado: (2024)

Learning Structural Latent Points for Efficient Visual Representations in Robotic Manipulation
por: Jiang, Yicheng, et al.
Publicado: (2026)

MVISTA-4D: View-Consistent 4D World Model with Test-Time Action Inference for Robotic Manipulation
por: Wang, Jiaxu, et al.
Publicado: (2026)

Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing
por: Kim, Wall, et al.
Publicado: (2026)

Decision MetaMamba: Enhancing Selective SSM in Offline RL with Heterogeneous Sequence Mixing
por: Kim, Wall, et al.
Publicado: (2024)

Should Decision-Makers Reveal Classifiers in Online Strategic Classification?
por: Shao, Han, et al.
Publicado: (2025)