paper-with-me

Papers

MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios

2025-11-09 · Xuantang Xiong, Ni Mu, Runpeng Xie, Senhao Yang, Yaqing Wang, Lexiang Wang, Yao Luan, Siyuan Li, Shuang Xu, Yiqin Yang, Bo Xu arxiv

Model-based reinforcement learning (MBRL) is a crucial approach to enhance the generalization capabilities and improve the sample efficiency of RL algorithms. However, current MBRL methods focus primarily on building world models for single tasks and rarely address generalization across different scenarios. Building on the insight that dynamics within the same simulation engine share inherent properties, we attempt to construct a unified world model capable of generalizing across different scenarios, named Meta-Regularized Contextual World-Model (MrCoM). This method first decomposes the latent state space into various components based on the dynamic characteristics, thereby enhancing the accuracy of world-model prediction. Further, MrCoM adopts meta-state regularization to extract unified representation of scenario-relevant information, and meta-value regularization to align world-model optimization with policy learning across diverse scenario objectives. We theoretically analyze the generalization error upper bound of MrCoM in multi-scenario settings. We systematically evaluate our algorithm's generalization ability across diverse scenarios, demonstrating significantly better performance than previous state-of-the-art methods.

📄 PDF Abstract BibTeX arXiv:2511.06252

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Generalizing Reward Modeling for Out-of-Distribution Preference Learning

2024-02-22 · Chen Jia

Preference learning (PL) with large language models (LLMs) aims to align the LLMs' generations with human preferences. Previous work on reinforcement learning from human feedback (RLHF) has demonstrated promising results…

Bilevel OptimizationMeta-LearningText Generation

Predicting Microbial Ontology and Pathogen Risk from Environmental Metadata with Large Language Models

2025-07-29 · Hyunwoo Yoo, Gail L. Rosen arxiv

Traditional machine learning models struggle to generalize in microbiome studies where only metadata is available, especially in small-sample settings or across studies with heterogeneous label formats. In this work, we …

Parameterizing Non-Parametric Meta-Reinforcement Learning Tasks via Subtask Decomposition

2023-09-21 · NeurIPS 2023 11

Meta-reinforcement learning (meta-RL) techniques have demonstrated remarkable success in generalizing deep reinforcement learning across a range of tasks. Nevertheless, these methods often struggle to generalize beyond t…

MAMBA: an Effective World Model Approach for Meta-Reinforcement Learning

2024-03-14 · Zohar Rimon, Tom Jurgenson, Orr Krupnik, Gilad Adler 외

Meta-reinforcement learning (meta-RL) is a promising framework for tackling challenging domains requiring efficient exploration. Existing meta-RL algorithms are characterized by low sample efficiency, and mostly focus on…

Efficient ExplorationMambaMeta Reinforcement Learningreinforcement-learning+1

MADOD: Generalizing OOD Detection to Unseen Domains via G-Invariance Meta-Learning

2024-11-02 · Haoliang Wang, Chen Zhao, Feng Chen

Real-world machine learning applications often face simultaneous covariate and semantic shifts, challenging traditional domain generalization and out-of-distribution (OOD) detection methods. We introduce Meta-learned Acr…

Domain GeneralizationMeta-LearningOut-of-Distribution DetectionOut of Distribution (OOD) Detection