Search Results for author: I-Jeng Wang

Found 10 papers, 1 papers with code

A Risk-Sensitive Approach to Policy Optimization

no code implementations19 Aug 2022 Jared Markowitz, Ryan W. Gardner, Ashley Llorens, Raman Arora, I-Jeng Wang

Without cost constraints, we find that pessimistic risk profiles can be used to reduce cost while improving total reward accumulation.

Decision Making

A Risk-Sensitive Policy Gradient Method

no code implementations29 Sep 2021 Jared Markowitz, Ryan Gardner, Ashley Llorens, Raman Arora, I-Jeng Wang

Standard deep reinforcement learning (DRL) agents aim to maximize expected reward, considering collected experiences equally in formulating a policy.

Decision Making

Learning a Group-Aware Policy for Robot Navigation

no code implementations22 Dec 2020 Kapil Katyal, Yuxiang Gao, Jared Markowitz, Sara Pohland, Corban Rivera, I-Jeng Wang, Chien-Ming Huang

Human-aware robot navigation promises a range of applications in which mobile robots bring versatile assistance to people in common human environments.

Social Navigation

Jacks of All Trades, Masters Of None: Addressing Distributional Shift and Obtrusiveness via Transparent Patch Attacks

no code implementations1 May 2020 Neil Fendley, Max Lennon, I-Jeng Wang, Philippe Burlina, Nathan Drenkow

We focus on the development of effective adversarial patch attacks and -- for the first time -- jointly address the antagonistic objectives of attack success and obtrusiveness via the design of novel semi-transparent patches.

TanksWorld: A Multi-Agent Environment for AI Safety Research

1 code implementation25 Feb 2020 Corban G. Rivera, Olivia Lyons, Arielle Summitt, Ayman Fatima, Ji Pak, William Shao, Robert Chalmers, Aryeh Englander, Edward W. Staley, I-Jeng Wang, Ashley J. Llorens

In this work, we introduce the AI safety TanksWorld as an environment for AI safety research with three essential aspects: competing performance objectives, human-machine teaming, and multi-agent competition.

Decision Making

Unsupervised Discovery, Control, and Disentanglement of Semantic Attributes with Applications to Anomaly Detection

no code implementations25 Feb 2020 William Paul, I-Jeng Wang, Fady Alajaji, Philippe Burlina

Our work focuses on unsupervised and generative methods that address the following goals: (a) learning unsupervised generative representations that discover latent factors controlling image semantic attributes, (b) studying how this ability to control attributes formally relates to the issue of latent factor disentanglement, clarifying related but dissimilar concepts that had been confounded in the past, and (c) developing anomaly detection methods that leverage representations learned in (a).

Anomaly Detection Disentanglement +2

Adversarial Examples in Remote Sensing

no code implementations28 May 2018 Wojciech Czaja, Neil Fendley, Michael Pekala, Christopher Ratto, I-Jeng Wang

This paper considers attacks against machine learning algorithms used in remote sensing applications, a domain that presents a suite of challenges that are not fully addressed by current research focused on natural image data such as ImageNet.

Satellite Image Classification

Combining Deep Universal Features, Semantic Attributes, and Hierarchical Classification for Zero-Shot Learning

no code implementations8 Dec 2017 Jared Markowitz, Aurora C. Schmidt, Philippe M. Burlina, I-Jeng Wang

We address zero-shot (ZS) learning, building upon prior work in hierarchical classification by combining it with approaches based on semantic attribute estimation.

General Classification Zero-Shot Learning

Automatic Dimension Selection for a Non-negative Factorization Approach to Clustering Multiple Random Graphs

no code implementations24 Jun 2014 Nam H. Lee, I-Jeng Wang, Youngser Park, Care E. Priebe, Michael Rosen

We consider a problem of grouping multiple graphs into several clusters using singular value thesholding and non-negative factorization.

Model Selection

Techniques for clustering interaction data as a collection of graphs

no code implementations24 Jun 2014 Nam H. Lee, Carey Priebe, Youngser Park, I-Jeng Wang, Michael Rosen

A natural approach to analyze interaction data of form "what-connects-to-what-when" is to create a time-series (or rather a sequence) of graphs through temporal discretization (bandwidth selection) and spatial discretization (vertex contraction).

Community Detection Model Selection +1

Cannot find the paper you are looking for? You can Submit a new open access paper.