Výsledky vyhledávání - "Ferguson, Craig"

Report

Computational Empathy Counteracts the Negative Effects of Anger on Creative Problem Solving

Autor: Groh, Matthew, Ferguson, Craig, Lewis, Robert, Picard, Rosalind

How does empathy influence creative problem solving? We introduce a computational empathy intervention based on context-specific affective mimicry and perspective taking by a virtual agent appearing in the form of a well-dressed polar bear. In an onl

Externí odkaz: http://arxiv.org/abs/2208.07178

Zobrazit plný text záznamu

Periodical

Late Bloomer.

Autor: Alston, Joshua

Publikováno v: Newsweek. 4/21/2008, Vol. 151 Issue 16, p54-56. 3p. 2 Color Photographs.

Zobrazit plný text záznamu

Plný text ve formátu HTML

Report

Human-centric Dialog Training via Offline Reinforcement Learning

Autor: Jaques, Natasha, Shen, Judy Hanwen, Ghandeharioun, Asma, Ferguson, Craig, Lapedriza, Agata, Jones, Noah, Gu, Shixiang Shane, Picard, Rosalind

How can we train a dialog model to produce better conversations by learning from human feedback, without the risk of humans teaching it harmful chat behaviors? We start by hosting models online, and gather human feedback from real-time, open-ended co

Externí odkaz: http://arxiv.org/abs/2010.05848

Zobrazit plný text záznamu

Report

Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog

Autor: Jaques, Natasha, Ghandeharioun, Asma, Shen, Judy Hanwen, Ferguson, Craig, Lapedriza, Agata, Jones, Noah, Gu, Shixiang, Picard, Rosalind

Most deep reinforcement learning (RL) systems are not able to learn effectively from off-policy data, especially if they cannot explore online in the environment. These are critical shortcomings for applying RL to real-world problems where collecting

Externí odkaz: http://arxiv.org/abs/1907.00456

Zobrazit plný text záznamu

Report

Approximating Interactive Human Evaluation with Self-Play for Open-Domain Dialog Systems

Autor: Ghandeharioun, Asma, Shen, Judy Hanwen, Jaques, Natasha, Ferguson, Craig, Jones, Noah, Lapedriza, Agata, Picard, Rosalind

Building an open-domain conversational agent is a challenging problem. Current evaluation methods, mostly post-hoc judgments of static conversation, do not capture conversation quality in a realistic interactive context. In this paper, we investigate

Externí odkaz: http://arxiv.org/abs/1906.09308

Zobrazit plný text záznamu