Imagen de Portada

SPHERE: Mitigating the Loss of Spectral Plasticity in Mixture-of-Experts for Deep Reinforcement Learning

Fuente: arXiv

Guardado en:

Detalles Bibliográficos
Autores principales:	Luo, Lirui, Zhang, Guoxi, Xu, Hongming, Fang, Cong, Li, Qing
Formato:	Preprint
Publicado:	2026
Materias:	Machine Learning
Acceso en línea:	Acceder al recurso
Etiquetas:	Agregar Etiqueta Sin Etiquetas, Sea el primero en etiquetar este registro!

Ejemplares similares

MVR: Multi-view Video Reward Shaping for Reinforcement Learning
por: Luo, Lirui, et al.
Publicado: (2026)

End-to-End Neuro-Symbolic Reinforcement Learning with Textual Explanations
por: Luo, Lirui, et al.
Publicado: (2024)

Mitigating Plasticity Loss in Continual Reinforcement Learning by Reducing Churn
por: Tang, Hongyao, et al.
Publicado: (2025)

Plasticity Loss in Deep Reinforcement Learning: A Survey
por: Klein, Timo, et al.
Publicado: (2024)

A Study of Plasticity Loss in On-Policy Deep Reinforcement Learning
por: Juliani, Arthur, et al.
Publicado: (2024)

The Rank and Gradient Lost in Non-stationarity: Sample Weight Decay for Mitigating Plasticity Loss in Reinforcement Learning
por: Wu, Zihao, et al.
Publicado: (2026)

Mixture-of-Experts Meets In-Context Reinforcement Learning
por: Wu, Wenhao, et al.
Publicado: (2025)

Towards Stable and Effective Reinforcement Learning for Mixture-of-Experts
por: Zhang, Di, et al.
Publicado: (2025)

MENTOR: Mixture-of-Experts Network with Task-Oriented Perturbation for Visual Reinforcement Learning
por: Huang, Suning, et al.
Publicado: (2024)

Multi-Task Reinforcement Learning with Mixture of Orthogonal Experts
por: Hendawy, Ahmed, et al.
Publicado: (2023)

A Distance-based Anomaly Detection Framework for Deep Reinforcement Learning
por: Zhang, Hongming, et al.
Publicado: (2021)

Ensemble and Mixture-of-Experts DeepONets For Operator Learning
por: Sharma, Ramansh, et al.
Publicado: (2024)

Rethinking Plasticity in Deep Reinforcement Learning
por: He, Zhiqiang
Publicado: (2026)

Coupling Experts and Routers in Mixture-of-Experts via an Auxiliary Loss
por: Lv, Ang, et al.
Publicado: (2025)

Auxiliary-Loss-Free Load Balancing Strategy for Mixture-of-Experts
por: Wang, Lean, et al.
Publicado: (2024)

Neuron-level Balance between Stability and Plasticity in Deep Reinforcement Learning
por: Lan, Jiahua, et al.
Publicado: (2025)

VickreyFeedback: Cost-efficient Data Construction for Reinforcement Learning from Human Feedback
por: Zhang, Guoxi, et al.
Publicado: (2024)

Fast Deep Mixtures of Gaussian Process Experts
por: Etienam, Clement, et al.
Publicado: (2020)

Fast Training of Mixture-of-Experts for Time Series Forecasting via Expert Loss Integration
por: Mahtout, Btissame El, et al.
Publicado: (2026)

Learning More Generalized Experts by Merging Experts in Mixture-of-Experts
por: Park, Sejik
Publicado: (2024)

Online Policy Learning from Offline Preferences
por: Zhang, Guoxi, et al.
Publicado: (2024)

Acquiring Diverse Skills using Curriculum Reinforcement Learning with Mixture of Experts
por: Celik, Onur, et al.
Publicado: (2024)

Learning under Singularity: An Information Criterion improving WBIC and sBIC
por: Liu, Lirui, et al.
Publicado: (2024)

Plasticine: Accelerating Research in Plasticity-Motivated Deep Reinforcement Learning
por: Yuan, Mingqi, et al.
Publicado: (2025)

Addressing Spectral Bias of Deep Neural Networks by Multi-Grade Deep Learning
por: Fang, Ronglong, et al.
Publicado: (2024)

Deep Clustering Survival Machines with Interpretable Expert Distributions
por: Hou, Bojian, et al.
Publicado: (2023)

Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts
por: He, Shwai, et al.
Publicado: (2025)

Revisiting Clustering of Neural Bandits: Selective Reinitialization for Mitigating Loss of Plasticity
por: Su, Zhiyuan, et al.
Publicado: (2025)

Hierarchical Mixture of Experts: Generalizable Learning for High-Level Synthesis
por: Li, Weikai, et al.
Publicado: (2024)

Robust Exploration in Directed Controller Synthesis via Reinforcement Learning with Soft Mixture-of-Experts
por: Ubukata, Toshihide, et al.
Publicado: (2026)

Aggregation Alignment for Federated Learning with Mixture-of-Experts under Data Heterogeneity
por: Fang, Zihan, et al.
Publicado: (2026)

Mastering Massive Multi-Task Reinforcement Learning via Mixture-of-Expert Decision Transformer
por: Kong, Yilun, et al.
Publicado: (2025)

Theory on Mixture-of-Experts in Continual Learning
por: Li, Hongbo, et al.
Publicado: (2024)

Mitigating Information Loss in Tree-Based Reinforcement Learning via Direct Optimization
por: Marton, Sascha, et al.
Publicado: (2024)

Generalizing GNNs with Tokenized Mixture of Experts
por: Guo, Xiaoguang, et al.
Publicado: (2026)

GraphMoRE: Mitigating Topological Heterogeneity via Mixture of Riemannian Experts
por: Guo, Zihao, et al.
Publicado: (2024)

Mixture of A Million Experts
por: He, Xu Owen
Publicado: (2024)

SARAD: LLM-Based Safety-Aware Hybrid Reinforcement Learning with Collision Prediction for Autonomous Driving
por: Wu, Kangyu, et al.
Publicado: (2026)

Mixture of Experts-augmented Deep Unfolding for Activity Detection in IRS-aided Systems
por: Ren, Zeyi, et al.
Publicado: (2025)

GraphMETRO: Mitigating Complex Graph Distribution Shifts via Mixture of Aligned Experts
por: Wu, Shirley, et al.
Publicado: (2023)