158 citations · 365 across the 20 of their papers we have counts for
23 papers
Persona-Guided LLM Agents for Task-Oriented Dialogue
Maryam Shoaeinaeini, Brent Harrison, A. B. Siddique
Prior work has shown that large language models (LLMs) can express diverse personality traits in open-ended text generation. However, it remains unclear whether they can do so in a…
The Goofus & Gallant Story Corpus for Practical Value Alignment
Md Sultan Al Nahian, Tasmia Tasrin, Spencer Frazier +2
Values or principles are key elements of human society that influence people to behave and function according to an accepted standard set of social rules to maintain social order.…
Guiding Reinforcement Learning Using Uncertainty-Aware Large Language Models
Maryam Shoaeinaeini, Brent Harrison
Human guidance in reinforcement learning (RL) is often impractical for large-scale applications due to high costs and time constraints. Large Language Models (LLMs) offer a promisi…
Machine Learning Approaches for Principle Prediction in Naturally Occurring Stories
Md Sultan Al Nahian, Spencer Frazier, Brent Harrison +1
Value alignment is the task of creating autonomous systems whose values align with those of humans. Past work has shown that stories are a potentially rich source of information on…
StyleM: Stylized Metrics for Image Captioning Built with Contrastive N-grams
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 Style…
Using Non-Stationary Bandits for Learning in Repeated Cournot Games with Non-Stationary Demand
Kshitija Taywade, Brent Harrison, Judy Goldsmith
Many past attempts at modeling repeated Cournot games assume that demand is stationary. This does not align with real-world scenarios in which market demands can evolve over a prod…
Modelling Cournot Games as Multi-agent Multi-armed Bandits
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 a…
A Self-Explainable Stylish Image Captioning Framework via Multi-References
Chengxi Li, Brent Harrison
In this paper, we propose to build a stylish image captioning model through a Multi-style Multi modality mechanism (2M). We demonstrate that with 2M, we can build an effective styl…
Training Value-Aligned Reinforcement Learning Agents Using a Normative Prior
Md Sultan Al Nahian, Spencer Frazier, Brent Harrison +1
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 f…
Influencing Reinforcement Learning through Natural Language Guidance
Tasmia Tasrin, Md Sultan Al Nahian, Habarakadage Perera +1
Interactive reinforcement learning agents use human feedback or instruction to help them learn in complex environments. Often, this feedback comes in the form of a discrete signal…
3M: Multi-style image caption generation using Multi-modality features under Multi-UPDOWN model
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 DenseC…
Multi-agent Reinforcement Learning for Decentralized Stable Matching
Kshitija Taywade, Judy Goldsmith, Brent Harrison
In the real world, people/entities usually find matches independently and autonomously, such as finding jobs, partners, roommates, etc. It is possible that this search for matches…
Visual Question Answering Using Semantic Information from Image Descriptions
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 k…
Learning Norms from Stories: A Prior for Value Aligned Agents
Spencer Frazier, Md Sultan Al Nahian, Mark Riedl +1
Value alignment is a property of an intelligent agent indicating that it can only pursue goals and activities that are beneficial to humans. Traditional approaches to value alignme…
Smart Advertisement for Maximal Clicks in Online Social Networks Without User Data
Nathaniel Hudson, Hana Khamfroush, Brent Harrison +1
Click-through rate (CTR) prediction of advertisements on online social network platforms to optimize advertising is of much interest. Prior works build machine learning models that…
A Hierarchical Approach for Visual Storytelling Using Image Description
Md Sultan Al Nahian, Tasmia Tasrin, Sagar Gandhi +2
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. I…
Monte-Carlo Tree Search for Simulation-based Strategy Analysis
Alexander Zook, Brent Harrison, Mark O. Riedl
Games are often designed to shape player behavior in a desired way; however, it can be unclear how design decisions affect the space of behaviors in a game. Designers usually explo…
Automated Rationale Generation: A Technique for Explainable AI and its Effects on Human Perceptions
Upol Ehsan, Pradyumna Tambwekar, Larry Chan +2
Automated rationale generation is an approach for real-time explanation generation whereby a computational model learns to translate an autonomous agent's internal state and action…
Controllable Neural Story Plot Generation via Reward Shaping
Pradyumna Tambwekar, Murtaza Dhuliawala, Lara J. Martin +3
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…
Explore, Exploit or Listen: Combining Human Feedback and Policy Model to Speed up Deep Reinforcement Learning in 3D Worlds
Zhiyu Lin, Brent Harrison, Aaron Keech +1
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 lea…
Guiding Reinforcement Learning Exploration Using Natural Language
Brent Harrison, Upol Ehsan, Mark O. Riedl
In this work we present a technique to use natural language to help reinforcement learning generalize to unseen environments. This technique uses neural machine translation, specif…
Event Representations for Automated Story Generation with Deep Neural Nets
Lara J. Martin, Prithviraj Ammanabrolu, Xinyu Wang +4
Automated story generation is the problem of automatically selecting a sequence of events, actions, or words that can be told as a story. We seek to develop a system that can gener…
Enter the Matrix: Safely Interruptible Autonomous Systems via Virtualization
Mark O. Riedl, Brent Harrison
Autonomous systems that operate around humans will likely always rely on kill switches that stop their execution and allow them to be remote-controlled for the safety of humans or…