skip to main content

Explore Research Products in the NSF-PAR

Title: Visual Transfer for Reinforcement Learning via Wasserstein Domain Confusion
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 both the easy and hard settings of of 16 OpenAI Procgen environments.  more » « less
Award ID(s):
1717569
NSF-PAR ID:
10310141
Author(s) / Creator(s):
;
Date Published:
Journal Name:
Proceedings of the Thirty-Fifth AAAI Conference on Artificial Intelligence
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ( , Information systems frontiers)
    null (Ed.)
    Convolutional Neural Network (CNN) models and many accessible large-scale public visual datasets have brought lots of research work to a remarkable new stage. Benefited from well-trained CNN models, small training datasets can learn comprehensive features by utilizing the preliminary features from transfer learning. However, the performance is not guaranteed when taking these features to construct a new model, as the differences always exist between the source and target domains. In this paper, we propose to build an Evolution Programming-based framework to address various challenges. This framework automates both the feature learning and model building processes. It first identifies the most valuable features from pre-trained models and then constructs a suitable model to understand the characteristic features for different tasks. Each model differs in numerous ways. Overall, the experimental results effectively reach optimal solutions, demonstrating that a time-consuming task could also be conducted by an automated process that exceeds the human ability. 
    more » « less
  2. ; ( , 2022 IEEE 46th Annual Computers, Software, and Applications Conference (COMPSAC))
    Activity Recognition (AR) models perform well with a large number of available training instances. However, in the presence of sensor heterogeneity, sensing biasness and variability of human behaviors and activities and unseen activity classes pose key challenges to adopting and scaling these pre-trained activity recognition models in the new environment. These challenging unseen activities recognition problems are addressed by applying transfer learning techniques that leverage a limited number of annotated samples and utilize the inherent structural patterns among activities within and across the source and target domains. This work proposes a novel AR framework that uses the pre-trained deep autoencoder model and generates features from source and target activity samples. Furthermore, this AR frame-work establishes correlations among activities between the source and target domain by exploiting intra- and inter-class knowledge transfer to mitigate the number of labeled samples and recognize unseen activities in the target domain. We validated the efficacy and effectiveness of our AR framework with three real-world data traces (Daily and Sports, Opportunistic, and Wisdm) that contain 41 users and 26 activities in total. Our AR framework achieves performance gains ≈ 5-6% with 111, 18, and 70 activity samples (20 % annotated samples) for Das, Opp, and Wisdm datasets. In addition, our proposed AR framework requires 56, 8, and 35 fewer activity samples (10% fewer annotated examples) for Das, Opp, and Wisdm, respectively, compared to the state-of-the-art Untran model. 
    more » « less
  3. ; ( , Annual Conference of the PHM Society)
    null (Ed.)
    Given its demonstrated ability in analyzing and revealing patterns underlying data, Deep Learning (DL) has been increasingly investigated to complement physics-based models in various aspects of smart manufacturing, such as machine condition monitoring and fault diagnosis, complex manufacturing process modeling, and quality inspection. However, successful implementation of DL techniques relies greatly on the amount, variety, and veracity of data for robust network training. Also, the distributions of data used for network training and application should be identical to avoid the internal covariance shift problem that reduces the network performance applicability. As a promising solution to address these challenges, Transfer Learning (TL) enables DL networks trained on a source domain and task to be applied to a separate target domain and task. This paper presents a domain adversarial TL approach, based upon the concepts of generative adversarial networks. In this method, the optimizer seeks to minimize the loss (i.e., regression or classification accuracy) across the labeled training examples from the source domain while maximizing the loss of the domain classifier across the source and target data sets (i.e., maximizing the similarity of source and target features). The developed domain adversarial TL method has been implemented on a 1-D CNN backbone network and evaluated for prediction of tool wear propagation, using NASA's milling dataset. Performance has been compared to other TL techniques, and the results indicate that domain adversarial TL can successfully allow DL models trained on certain scenarios to be applied to new target tasks. 
    more » « less
  4. ; ; ; ; ; ; ; ; ( , Data)
    null (Ed.)
    Sea ice acts as both an indicator and an amplifier of climate change. High spatial resolution (HSR) imagery is an important data source in Arctic sea ice research for extracting sea ice physical parameters, and calibrating/validating climate models. HSR images are difficult to process and manage due to their large data volume, heterogeneous data sources, and complex spatiotemporal distributions. In this paper, an Arctic Cyberinfrastructure (ArcCI) module is developed that allows a reliable and efficient on-demand image batch processing on the web. For this module, available associated datasets are collected and presented through an open data portal. The ArcCI module offers an architecture based on cloud computing and big data components for HSR sea ice images, including functionalities of (1) data acquisition through File Transfer Protocol (FTP) transfer, front-end uploading, and physical transfer; (2) data storage based on Hadoop distributed file system and matured operational relational database; (3) distributed image processing including object-based image classification and parameter extraction of sea ice features; (4) 3D visualization of dynamic spatiotemporal distribution of extracted parameters with flexible statistical charts. Arctic researchers can search and find arctic sea ice HSR image and relevant metadata in the open data portal, obtain extracted ice parameters, and conduct visual analytics interactively. Users with large number of images can leverage the service to process their image in high performance manner on cloud, and manage, analyze results in one place. The ArcCI module will assist domain scientists on investigating polar sea ice, and can be easily transferred to other HSR image processing research projects. 
    more » « less
  5. ; ; ( , Proceedings of Machine Learning Research)
    Wasserstein Barycenter is a principled approach to represent the weighted mean of a given set of probability distributions, utilizing the geometry induced by optimal transport. In this work, we present a novel scalable algorithm to approximate the Wasserstein Barycenters aiming at highdimensional applications in machine learning. Our proposed algorithm is based on the Kantorovich dual formulation of the Wasserstein-2 distance as well as a recent neural network architecture, input convex neural network, that is known to parametrize convex functions. The distinguishing features of our method are: i) it only requires samples from the marginal distributions; ii) unlike the existing approaches, it represents the Barycenter with a generative model and can thus generate infinite samples from the barycenter without querying the marginal distributions; iii) it works similar to Generative Adversarial Model in one marginal case. We demonstrate the efficacy of our algorithm by comparing it with the state-of-art methods in multiple experiments. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email