paper-with-me

Papers

Task-Aware Virtual Training: Enhancing Generalization in Meta-Reinforcement Learning for Out-of-Distribution Tasks

2025-02-05 · Jeongmo Kim, Yisak Park, Minung Kim, Seungyul Han

Meta reinforcement learning aims to develop policies that generalize to unseen tasks sampled from a task distribution. While context-based meta-RL methods improve task representation using task latents, they often struggle with out-of-distribution (OOD) tasks. To address this, we propose Task-Aware Virtual Training (TAVT), a novel algorithm that accurately captures task characteristics for both training and OOD scenarios using metric-based representation learning. Our method successfully preserves task characteristics in virtual tasks and employs a state regularization technique to mitigate overestimation errors in state-varying environments. Numerical results demonstrate that TAVT significantly enhances generalization to OOD tasks across various MuJoCo and MetaWorld environments.

📄 PDF Abstract BibTeX arXiv:2502.02834

Code (1)

sunwoolee0504/wall pytorch

Tasks

Meta Reinforcement LearningMuJoCoRepresentation Learning

Similar Papers 제목 키워드 기반

Dynamic Worlds, Dynamic Humans: Generating Virtual Human-Scene Interaction Motion in Dynamic Scenes

2026-01-27 · Yin Wang, Zhiying Leng, Haitian Liu, Frederick W. B. Li 외 arxiv

Scenes are continuously undergoing dynamic changes in the real world. However, existing human-scene interaction generation methods typically treat the scene as static, which deviates from reality. Inspired by world model…

Adversarial Data Augmentation for Single Domain Generalization via Lyapunov Exponent-Guided Optimization

2025-07-06 · Zuyu Zhang, Ning Chen, Yongshan Liu, Qinghua Zhang 외 arxiv

Single Domain Generalization (SDG) aims to develop models capable of generalizing to unseen target domains using only one source domain, a task complicated by substantial domain shifts and limited data diversity. Existin…

Domain GeneralizationData Augmentation

Enhancing Virtual Try-On with Synthetic Pairs and Error-Aware Noise Scheduling

2025-01-08 · CVPR 2025 1 · Nannan Li, Kevin J. Shih, Bryan A. Plummer

Given an isolated garment image in a canonical product view and a separate image of a person, the virtual try-on task aims to generate a new image of the person wearing the target garment. Prior virtual try-on works face…

Data AugmentationSchedulingVirtual Try-on

GA-SAM: Gradient-Strength based Adaptive Sharpness-Aware Minimization for Improved Generalization

2022-10-13 · Zhiyuan Zhang, Ruixuan Luo, Qi Su, Xu sun

Recently, Sharpness-Aware Minimization (SAM) algorithm has shown state-of-the-art generalization abilities in vision tasks. It demonstrates that flat minima tend to imply better generalization abilities. However, it has …

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…