Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion

2020-06-04 · Josh Roy, George Konidaris

We introduce Wasserstein Adversarial Proximal Policy Optimization (WAPPO), a novel algorithm for visual transfer in Reinforcement Learning that explicitly learns to align the distributions of extracted features between a source and target task. WAPPO approximates and minimizes the Wasserstein-1 distance between the distributions of features from source and target domains via a novel Wasserstein Confusion objective. WAPPO outperforms the prior state-of-the-art in visual transfer and successfully transfers policies across Visual Cartpole and two instantiations of 16 OpenAI Procgen environments.

📄 PDF Abstract BibTeX arXiv:2006.03465

Code (1)

ku2482/wappo.pytorch pytorch

Tasks

reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

DisRFM: Polar Riemannian Flow Matching for Structure-Preserving Graph Domain Adaptation

2026-01-31 · Yingxu Wang, Xinwang Liu, Mengzhu Wang, Siyang Gao 외 arxiv

Graph Domain Adaptation (GDA) aims to transfer graph classifiers across domains with both semantic and topological shifts. Existing Euclidean adversarial methods face two challenges: Structural Degeneration, where domain…

Representation Learning GRAPH DOMAIN ADAPTATION

Wasserstein Distance based Deep Adversarial Transfer Learning for Intelligent Fault Diagnosis

2019-03-02 · Cheng Cheng, Beitong Zhou, Guijun Ma, Dongrui Wu 외

The demand of artificial intelligent adoption for condition-based maintenance strategy is astonishingly increased over the past few years. Intelligent fault diagnosis is one critical topic of maintenance solution for mec…

Fault Diagnosis Transfer Learning

Wasserstein Selective Transfer Learning for Cross-domain Text Mining

2021-11-01 · EMNLP 2021 11 · Lingyun Feng, Minghui Qiu, Yaliang Li, Haitao Zheng 외

Transfer learning (TL) seeks to improve the learning of a data-scarce target domain by using information from source domains. However, the source and target domains usually have different data distributions, which may le…

Transfer Learning

Do Open-Vocabulary Detectors Transfer to Aerial Imagery? A Comparative Evaluation

2026-01-13 · Christos Tsourveloudis arxiv

Open-vocabulary object detection (OVD) enables zero-shot recognition of novel categories through vision-language models, achieving strong performance on natural images. However, transferability to aerial imagery remains …

Visual Localization Prompt Engineering Object Detection

Domain Confusion with Self Ensembling for Unsupervised Adaptation

2018-10-10 · Jiawei Wang, Zhaoshui He, Chengjian Feng, Zhouping Zhu 외

Data collection and annotation are time-consuming in machine learning, expecially for large scale problem. A common approach for this problem is to transfer knowledge from a related labeled domain to a target one. There …

Domain Adaptation Unsupervised Domain Adaptation