arXiv subjects

Ofra Amir

Publications and source records attributed to Ofra Amir.

24 records · Page 2Linked to original sources

arXiv2021

"I Don't Think So": Summarizing Policy Disagreements for Agent Comparison

With Artificial Intelligence on the rise, human interaction with autonomous agents becomes more frequent. Effective human-agent collaboration requires users to understand the agent's behavior, as failing to do so may cause reduced productivity, misuse or frustration. Agent strategy summarization methods are used to describe the strategy of an agent to its destined user through demonstration. A summary's objective is to maximize the user's understanding of the agent's aptitude by showcasing its behaviour in a selected set of world states. While shown to be useful, we show that current methods are limited when tasked with comparing between agents, as each summary is independently generated for a specific agent. In this paper, we propose a novel method for generating dependent and contrastive summaries that emphasize the differences between agent policies by identifying states in which the agents disagree on the best course of action. We conduct user studies to assess the usefulness of disagreement-based summaries for identifying superior agents and conveying agent differences. Results show disagreement-based summaries lead to improved user performance compared to summaries generated using HIGHLIGHTS, a strategy summarization algorithm which generates summaries for each agent independently.

cs.AI↗

arXiv2021

VoterFraud2020: a Multi-modal Dataset of Election Fraud Claims on Twitter

The wide spread of unfounded election fraud claims surrounding the U.S. 2020 election had resulted in undermining of trust in the election, culminating in violence inside the U.S. capitol. Under these circumstances, it is critical to understand the discussions surrounding these claims on Twitter, a major platform where the claims were disseminated. To this end, we collected and released the VoterFraud2020 dataset, a multi-modal dataset with 7.6M tweets and 25.6M retweets from 2.6M users related to voter fraud claims. To make this data immediately useful for a diverse set of research projects, we further enhance the data with cluster labels computed from the retweet graph, each user's suspension status, and the perceptual hashes of tweeted images. The dataset also includes aggregate data for all external links and YouTube videos that appear in the tweets. Preliminary analyses of the data show that Twitter's user suspension actions mostly affected a specific community of voter fraud claim promoters, and exposes the most common URLs, images and YouTube videos shared in the data.

cs.SI↗

arXiv2020

Learning to Characterize Matching Experts

Matching is a task at the heart of any data integration process, aimed at identifying correspondences among data elements. Matching problems were traditionally solved in a semi-automatic manner, with correspondences being generated by matching algorithms and outcomes subsequently validated by human experts. Human-in-the-loop data integration has been recently challenged by the introduction of big data and recent studies have analyzed obstacles to effective human matching and validation. In this work we characterize human matching experts, those humans whose proposed correspondences can mostly be trusted to be valid. We provide a novel framework for characterizing matching experts that, accompanied with a novel set of features, can be used to identify reliable and valuable human experts. We demonstrate the usefulness of our approach using an extensive empirical evaluation. In particular, we show that our approach can improve matching results by filtering out inexpert matchers.

cs.DB↗

arXiv2020

Local and Global Explanations of Agent Behavior: Integrating Strategy Summaries with Saliency Maps

With advances in reinforcement learning (RL), agents are now being developed in high-stakes application domains such as healthcare and transportation. Explaining the behavior of these agents is challenging, as the environments in which they act have large state spaces, and their decision-making can be affected by delayed rewards, making it difficult to analyze their behavior. To address this problem, several approaches have been developed. Some approaches attempt to convey the $\textit{global}$ behavior of the agent, describing the actions it takes in different states. Other approaches devised $\textit{local}$ explanations which provide information regarding the agent's decision-making in a particular state. In this paper, we combine global and local explanation methods, and evaluate their joint and separate contributions, providing (to the best of our knowledge) the first user study of combined local and global explanations for RL agents. Specifically, we augment strategy summaries that extract important trajectories of states from simulations of the agent with saliency maps which show what information the agent attends to. Our results show that the choice of what states to include in the summary (global information) strongly affects people's understanding of agents: participants shown summaries that included important states significantly outperformed participants who were presented with agent behavior in a randomly set of chosen world-states. We find mixed results with respect to augmenting demonstrations with saliency maps (local information), as the addition of saliency maps did not significantly improve performance in most cases. However, we do find some evidence that saliency maps can help users better understand what information the agent relies on in its decision making, suggesting avenues for future work that can further improve explanations of RL agents.

cs.LG↗

arXiv2019

Exploring Computational User Models for Agent Policy Summarization

AI agents are being developed to support high stakes decision-making processes from driving cars to prescribing drugs, making it increasingly important for human users to understand their behavior. Policy summarization methods aim to convey strengths and weaknesses of such agents by demonstrating their behavior in a subset of informative states. Some policy summarization methods extract a summary that optimizes the ability to reconstruct the agent's policy under the assumption that users will deploy inverse reinforcement learning. In this paper, we explore the use of different models for extracting summaries. We introduce an imitation learning-based approach to policy summarization; we demonstrate through computational simulations that a mismatch between the model used to extract a summary and the model used to reconstruct the policy results in worse reconstruction quality; and we demonstrate through a human-subject study that people use different models to reconstruct policies in different contexts, and that matching the summary extraction model to these can improve performance. Together, our results suggest that it is important to carefully consider user models in policy summarization.

cs.LG↗

arXiv2018

Efficient Crowdsourcing via Proxy Voting

Crowdsourcing platforms offer a way to label data by aggregating answers of multiple unqualified workers. We introduce a \textit{simple} and \textit{budget efficient} crowdsourcing method named Proxy Crowdsourcing (PCS). PCS collects answers from two sets of workers: \textit{leaders} (a.k.a proxies) and \textit{followers}. Each leader completely answers the survey while each follower answers only a small subset of it. We then weigh every leader according to the number of followers to which his answer are closest, and aggregate the answers of the leaders using any standard aggregation method (e.g., Plurality for categorical labels or Mean for continuous labels). We compare empirically the performance of PCS to unweighted aggregation, keeping the total number of questions (the budget) fixed. We show that PCS improves the accuracy of aggregated answers across several datasets, both with categorical and continuous labels. Overall, our suggested method improves accuracy while being simple and easy to implement.

cs.GT↗