Image de couverture de livre

Less is More: Clustered Cross-Covariance Control for Offline RL

Fuente: arXiv

Enregistré dans:

Détails bibliographiques
Auteurs principaux:	Qiao, Nan, Yue, Sheng, Wang, Shuning, Deng, Yongheng, Ren, Ju
Format:	Preprint
Publié:	2026
Sujets:	Machine Learning
Accès en ligne:	Acceder al recurso
Tags:	Ajouter un tag Pas de tags, Soyez le premier à ajouter un tag!

Documents similaires

AdamO: A Collapse-Suppressed Optimizer for Offline RL
par: Qiao, Nan, et autres
Publié: (2026)

Federated Offline Policy Optimization with Dual Regularization
par: Yue, Sheng, et autres
Publié: (2024)

FOVA: Offline Federated Reinforcement Learning with Mixed-Quality Data
par: Qiao, Nan, et autres
Publié: (2025)

FORLER: Federated Offline Reinforcement Learning with Q-Ensemble and Actor Rectification
par: Qiao, Nan, et autres
Publié: (2026)

LIMR: Less is More for RL Scaling
par: Li, Xuefeng, et autres
Publié: (2025)

AugFL: Augmenting Federated Learning with Pretrained Models
par: Yue, Sheng, et autres
Publié: (2025)

OLLIE: Imitation Learning from Offline Pretraining to Online Finetuning
par: Yue, Sheng, et autres
Publié: (2024)

SCOPE-RL: Stable and Quantitative Control of Policy Entropy in RL Post-Training
par: Wang, Chen, et autres
Publié: (2025)

How to Leverage Diverse Demonstrations in Offline Imitation Learning
par: Yue, Sheng, et autres
Publié: (2024)

Watch Less, Feel More: Sim-to-Real RL for Generalizable Articulated Object Manipulation via Motion Adaptation and Impedance Control
par: Do, Tan-Dzung, et autres
Publié: (2025)

Decoupled Prioritized Resampling for Offline RL
par: Yue, Yang, et autres
Publié: (2023)

Cloud-Edge Collaborative Large Models for Robust Photovoltaic Power Forecasting
par: Qiao, Nan, et autres
Publié: (2026)

Optimistic Critic Reconstruction and Constrained Fine-Tuning for General Offline-to-Online RL
par: Luo, Qin-Wen, et autres
Publié: (2024)

Learning to Trust Bellman Updates: Selective State-Adaptive Regularization for Offline RL
par: Luo, Qin-Wen, et autres
Publié: (2025)

Making Offline RL Online: Collaborative World Models for Offline Visual Reinforcement Learning
par: Wang, Qi, et autres
Publié: (2023)

Less-to-More Generalization: Unlocking More Controllability by In-Context Generation
par: Wu, Shaojin, et autres
Publié: (2025)

Less is More: Hop-Wise Graph Attention for Scalable and Generalizable Learning on Circuits
par: Deng, Chenhui, et autres
Publié: (2024)

Improving Offline RL by Blending Heuristics
par: Geng, Sinong, et autres
Publié: (2023)

Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models
par: Zhang, Hongyin, et autres
Publié: (2025)

Augmenting Offline RL with Unlabeled Data
par: Wang, Zhao, et autres
Publié: (2024)

Dataset Clustering for Improved Offline Policy Learning
par: Wang, Qiang, et autres
Publié: (2024)

Reinformer: Max-Return Sequence Modeling for Offline RL
par: Zhuang, Zifeng, et autres
Publié: (2024)

Budgeting Counterfactual for Offline RL
par: Liu, Yao, et autres
Publié: (2023)

Less is More: Non-uniform Road Segments are Efficient for Bus Arrival Prediction
par: Huang, Zhen, et autres
Publié: (2025)

Decision Mamba: A Multi-Grained State Space Model with Self-Evolution Regularization for Offline RL
par: Lv, Qi, et autres
Publié: (2024)

Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies
par: Zhu, Lingwei, et autres
Publié: (2025)

DISA: Offline Importance Sampling for Distribution-Matching LLM-RL
par: Wang, Shaobo, et autres
Publié: (2026)

When Are RL Hyperparameters Benign? A Study in Offline Goal-Conditioned RL
par: Töpperwien, Jan Malte, et autres
Publié: (2026)

Are Expressive Models Truly Necessary for Offline RL?
par: Wang, Guan, et autres
Publié: (2024)

Less is More: Unlocking Specialization of Time Series Foundation Models via Structured Pruning
par: Zhao, Lifan, et autres
Publié: (2025)

Quantize What Counts: More for Keys, Less for Values
par: Hariri, Mohsen, et autres
Publié: (2025)

Selective Uncertainty Propagation in Offline RL
par: Krishnamurthy, Sanath Kumar, et autres
Publié: (2023)

Paying Less Generalization Tax: A Cross-Domain Generalization Study of RL Training for LLM Agents
par: Liu, Zhihan, et autres
Publié: (2026)

Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
par: Qiao, Zhongjian, et autres
Publié: (2026)

Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
par: Gupta, Aaryan, et autres
Publié: (2025)

Offline RL via Feature-Occupancy Gradient Ascent
par: Neu, Gergely, et autres
Publié: (2024)

Gains: Fine-grained Federated Domain Adaptation in Open Set
par: Zhong, Zhengyi, et autres
Publié: (2025)

Less is More: Improving LLM Alignment via Preference Data Selection
par: Deng, Xun, et autres
Publié: (2025)

An Empirical Study on the Effectiveness of Incorporating Offline RL As Online RL Subroutines
par: Su, Jianhai, et autres
Publié: (2025)

Learning from Less: SINDy Surrogates in RL
par: Dixit, Aniket, et autres
Publié: (2025)