no code implementations • NAACL (ALVR) 2021 • Chengxi Li, Brent Harrison
In this paper, we propose an error causal inference method that could be used for finding dominant features for a faulty instance under a well-trained multi-modality input model, which could apply to any testing instance.
no code implementations • RANLP 2021 • Anton Vinogradov, Andrew Miles Byrd, Brent Harrison
Giving feedback to students is not just about marking their answers as correct or incorrect, but also finding mistakes in their thought process that led them to that incorrect answer.
no code implementations • 19 Nov 2022 • Md Sultan Al Nahian, Spencer Frazier, Brent Harrison, Mark Riedl
To do this, we extend a dataset that has been previously used to train a binary normative classifier with annotations of moral principles.
no code implementations • 4 Jan 2022 • Chengxi Li, Brent Harrison
In this paper, we build two automatic evaluation metrics for evaluating the association between a machine-generated caption and a ground truth stylized caption: OnlyStyle and StyleCIDEr.
no code implementations • 3 Jan 2022 • Kshitija Taywade, Brent Harrison, Judy Goldsmith
We found that using our proposed method, agents are able to swiftly change their course of action according to the changes in demand, and they also engage in collusive behavior in many simulations.
no code implementations • 1 Jan 2022 • Kshitija Taywade, Brent Harrison, Adib Bagh
We investigate the use of a multi-agent multi-armed bandit (MA-MAB) setting for modeling repeated Cournot oligopoly games, where the firms acting as agents choose from the set of arms representing production quantity (a discrete value).
no code implementations • 20 Oct 2021 • Chengxi Li, Brent Harrison
In this paper, we propose to build a stylish image captioning model through a Multi-style Multi modality mechanism (2M).
no code implementations • 19 Apr 2021 • Md Sultan Al Nahian, Spencer Frazier, Brent Harrison, Mark Riedl
As more machine learning agents interact with humans, it is increasingly a prospect that an agent trained to perform a task optimally, using only a measure of task performance as feedback, can violate societal norms for acceptable behavior or cause harm.
1 code implementation • 4 Apr 2021 • Tasmia Tasrin, Md Sultan Al Nahian, Habarakadage Perera, Brent Harrison
In this work, we explore how natural language advice can be used to provide a richer feedback signal to a reinforcement learning agent by extending policy shaping, a well-known Interactive reinforcement learning technique.
no code implementations • 20 Mar 2021 • Chengxi Li, Brent Harrison
In this paper, we build a multi-style generative model for stylish image captioning which uses multi-modality image features, ResNeXt features and text features generated by DenseCap.
no code implementations • 3 May 2020 • Kshitija Taywade, Judy Goldsmith, Brent Harrison
Along with conventional stable matching case where agents have strictly ordered preferences, we check the applicability of our approach for stable matching with incomplete lists and ties.
no code implementations • 23 Apr 2020 • Tasmia Tasrin, Md Sultan Al Nahian, Brent Harrison
In this work, we propose a deep neural architecture that uses an attention mechanism which utilizes region based image features, the natural language question asked, and semantic knowledge extracted from the regions of an image to produce open-ended answers for questions asked in a visual question answering (VQA) task.
no code implementations • 7 Dec 2019 • Spencer Frazier, Md Sultan Al Nahian, Mark Riedl, Brent Harrison
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans.
no code implementations • 26 Sep 2019 • Md Sultan Al Nahian, Tasmia Tasrin, Sagar Gandhi, Ryan Gaines, Brent Harrison
One of the primary challenges of visual storytelling is developing techniques that can maintain the context of the story over long event sequences to generate human-like stories.
no code implementations • 4 Aug 2019 • Alexander Zook, Brent Harrison, Mark O. Riedl
Using these case studies, we show how using simulated agents to model humans of varying skill levels allows us to extract metrics to describe game balance (in the case of Scrabble) and highlight potential design flaws (in the case of Cardonomicon).
no code implementations • 11 Jan 2019 • Upol Ehsan, Pradyumna Tambwekar, Larry Chan, Brent Harrison, Mark Riedl
The second study further explores user preferences between the generated rationales with regard to confidence in the autonomous agent, communicating failure and unexpected behavior.
1 code implementation • 27 Sep 2018 • Pradyumna Tambwekar, Murtaza Dhuliawala, Lara J. Martin, Animesh Mehta, Brent Harrison, Mark O. Riedl
Language-modeling--based approaches to story plot generation attempt to construct a plot by sampling from a language model (LM) to predict the next character, word, or sentence to add to the story.
no code implementations • 12 Sep 2017 • Zhiyu Lin, Brent Harrison, Aaron Keech, Mark O. Riedl
We describe a method to use discrete human feedback to enhance the performance of deep learning agents in virtual three-dimensional environments by extending deep-reinforcement learning to model the confidence and consistency of human feedback.
no code implementations • 26 Jul 2017 • Brent Harrison, Upol Ehsan, Mark O. Riedl
We then use this learned model to guide agent exploration using a modified version of policy shaping to make it more effective at learning in unseen environments.
1 code implementation • 5 Jun 2017 • Lara J. Martin, Prithviraj Ammanabrolu, Xinyu Wang, William Hancock, Shruti Singh, Brent Harrison, Mark O. Riedl
We then present a technique for automated story generation whereby we decompose the problem into the generation of successive events (event2event) and the generation of natural language sentences from events (event2sentence).
no code implementations • 30 Mar 2017 • Mark O. Riedl, Brent Harrison
It is theoretically possible for an autonomous system with sufficient sensor and effector capability that learn online using reinforcement learning to discover that the kill switch deprives it of long-term reward and thus learn to disable the switch or otherwise prevent a human operator from using the switch.
no code implementations • 25 Feb 2017 • Upol Ehsan, Brent Harrison, Larry Chan, Mark O. Riedl
Results of these evaluations show that neural machine translation is able to accurately generate rationalizations that describe agent behavior, and that rationalizations are more satisfying to humans than other alternative methods of explanation.