Cover Image

DeFlow: Decoupling Manifold Modeling and Value Maximization for Offline Policy Extraction

Fuente: arXiv

Saved in:

Bibliographic Details
Main Author:	Mu, Zhancun
Format:	Preprint
Published:	2026
Subjects:	Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Similar Items

Preserve Support, Not Correspondence: Dynamic Routing for Offline Reinforcement Learning
by: Mu, Zhancun, et al.
Published: (2026)

A Contextual Combinatorial Bandit Approach to Negotiation
by: Li, Yexin, et al.
Published: (2024)

ROCKET-2: Steering Visuomotor Policy via Cross-View Goal Alignment
by: Cai, Shaofei, et al.
Published: (2025)

Guided Flow Policy: Learning from High-Value Actions in Offline Reinforcement Learning
by: Tiofack, Franki Nguimatsia, et al.
Published: (2025)

Modular Diffusion Policy Training: Decoupling and Recombining Guidance and Diffusion for Offline RL
by: Chen, Zhaoyang, et al.
Published: (2025)

Pretrain Value, Not Reward: Decoupled Value Policy Optimization
by: Huang, Chenghua, et al.
Published: (2025)

Value-Guidance MeanFlow for Offline Multi-Agent Reinforcement Learning
by: Pang, Teng, et al.
Published: (2026)

DeFlow: Decoder of Scene Flow Network in Autonomous Driving
by: Zhang, Qingwen, et al.
Published: (2024)

Decoupled Prioritized Resampling for Offline RL
by: Yue, Yang, et al.
Published: (2023)

Diffusion Policies with Value-Conditional Optimization for Offline Reinforcement Learning
by: Ma, Yunchang, et al.
Published: (2025)

FlowQ: Energy-Guided Flow Policies for Offline Reinforcement Learning
by: Alles, Marvin, et al.
Published: (2025)

Residual Q-Learning: Offline and Online Policy Customization without Value
by: Li, Chenran, et al.
Published: (2023)

Manifold Clustering with Schatten p-norm Maximization
by: Li, Fangfang, et al.
Published: (2025)

Preference Goal Tuning: Post-Training as Latent Control for Frozen Policies
by: Zhao, Guangyu, et al.
Published: (2024)

Manifold-Constrained Energy-Based Transition Models for Offline Reinforcement Learning
by: Fang, Zeyu, et al.
Published: (2026)

Learning Design-Score Manifold to Guide Diffusion Models for Offline Optimization
by: Zhou, Tailin, et al.
Published: (2025)

OM2P: Offline Multi-Agent Mean-Flow Policy
by: Li, Zhuoran, et al.
Published: (2025)

Optimistic Model Rollouts for Pessimistic Offline Policy Optimization
by: Zhai, Yuanzhao, et al.
Published: (2024)

Safe Flow Q-Learning: Offline Safe Reinforcement Learning with Reachability-Based Flow Policies
by: Tayal, Mumuksh, et al.
Published: (2026)

One-Step Flow Q-Learning: Addressing the Diffusion Policy Bottleneck in Offline Reinforcement Learning
by: Nguyen, Thanh, et al.
Published: (2025)

Offline Diversity Maximization Under Imitation Constraints
by: Vlastelica, Marin, et al.
Published: (2023)

Manifold Sampling via Entropy Maximization
by: Braun, Cornelius V., et al.
Published: (2026)

Decoupled Guidance Diffusion for Adaptive Offline Safe Reinforcement Learning
by: Chen, Rufeng, et al.
Published: (2026)

Fat-to-Thin Policy Optimization: Offline RL with Sparse Policies
by: Zhu, Lingwei, et al.
Published: (2025)

Inference Time Policy Optimization for Offline RL with Differentiable World Models
by: Deb, Rohan, et al.
Published: (2026)

Diffusion Policies for Risk-Averse Behavior Modeling in Offline Reinforcement Learning
by: Chen, Xiaocong, et al.
Published: (2024)

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

Efficient Policy Evaluation with Offline Data Informed Behavior Policy Design
by: Liu, Shuze, et al.
Published: (2023)

GEM: Guided Expectation-Maximization for Behavior-Normalized Candidate Action Selection in Offline RL
by: Wang, Haoyu, et al.
Published: (2026)

Categorical Flow Matching on Statistical Manifolds
by: Cheng, Chaoran, et al.
Published: (2024)

Semi-Supervised Manifold Learning with Complexity Decoupled Chart Autoencoders
by: Schonsheck, Stefan C., et al.
Published: (2022)

Decoupling Feature Extraction and Classification Layers for Calibrated Neural Networks
by: Jordahn, Mikkel, et al.
Published: (2024)

Instrumental Variable Value Iteration for Causal Offline Reinforcement Learning
by: Liao, Luofeng, et al.
Published: (2021)

FOSP: Fine-tuning Offline Safe Policy through World Models
by: Cao, Chenyang, et al.
Published: (2024)

CROP: Conservative Reward for Model-based Offline Policy Optimization
by: Li, Hao, et al.
Published: (2023)

Distorted Distributional Policy Evaluation for Offline Reinforcement Learning
by: Iwaki, Ryo, et al.
Published: (2026)

Mildly Constrained Evaluation Policy for Offline Reinforcement Learning
by: Xu, Linjie, et al.
Published: (2023)

Active Reinforcement Learning Strategies for Offline Policy Improvement
by: Dukkipati, Ambedkar, et al.
Published: (2024)

Hypercube Policy Regularization Framework for Offline Reinforcement Learning
by: Shen, Yi, et al.
Published: (2024)

Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
by: Jing, Tan, et al.
Published: (2025)