1 code implementation • 29 Sep 2023 • Shengyi Huang, Jiayi Weng, Rujikorn Charakorn, Min Lin, Zhongwen Xu, Santiago Ontañón
Distributed Deep Reinforcement Learning (DRL) aims to leverage more computational resources to train autonomous agents with less training time.
no code implementations • 28 Aug 2023 • Yury Zemlyanskiy, Michiel de Jong, Luke Vilnis, Santiago Ontañón, William W. Cohen, Sumit Sanghai, Joshua Ainslie
Retrieval augmentation is a powerful but expensive method to make language models more knowledgeable about the world.
1 code implementation • 18 May 2023 • David Uthus, Santiago Ontañón, Joshua Ainslie, Mandy Guo
We present our work on developing a multilingual, efficient text-to-text transformer that is suitable for handling long inputs.
no code implementations • 17 Mar 2023 • Joshua Ainslie, Tao Lei, Michiel de Jong, Santiago Ontañón, Siddhartha Brahma, Yury Zemlyanskiy, David Uthus, Mandy Guo, James Lee-Thorp, Yi Tay, Yun-Hsuan Sung, Sumit Sanghai
Many natural language processing tasks benefit from long inputs, but processing long documents with Transformers is expensive -- not only due to quadratic attention complexity but also from applying feedforward and projection layers to every token.
Ranked #1 on Long-range modeling on SCROLLS
no code implementations • 18 Feb 2023 • Robert C. Gray, Jennifer Villareale, Thomas B. Fox, Diane H. Dallal, Santiago Ontañón, Danielle Arigo, Shahin Jabbari, Jichen Zhu
Our results indicate that our Shapley Bandits effectively mediates the Greedy Bandit Problem and achieves better user retention and motivation across the participants.
1 code implementation • 18 May 2022 • Shengyi Huang, Anssi Kanervisto, Antonin Raffin, Weixun Wang, Santiago Ontañón, Rousslan Fernand Julien Dossa
Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years.
no code implementations • 12 Nov 2021 • David Grethlein, Aleksanteri Sladek, Santiago Ontañón
In this paper we introduce a novel algorithm called Iterative Section Reduction (ISR) to automatically identify sub-intervals of spatiotemporal time series that are predictive of a target classification task.
no code implementations • 8 Oct 2021 • Luana Ruiz, Joshua Ainslie, Santiago Ontañón
Deep learning models generalize well to in-distribution data but struggle to generalize compositionally, i. e., to combine a set of learned primitives to solve more complex tasks.
1 code implementation • ACL 2022 • Santiago Ontañón, Joshua Ainslie, Vaclav Cvicek, Zachary Fisher
Several studies have reported the inability of Transformer models to generalize compositionally, a key type of generalization in many NLP tasks such as semantic parsing.
no code implementations • ACL 2021 • Juyong Kim, Pradeep Ravikumar, Joshua Ainslie, Santiago Ontañón
Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components.
4 code implementations • 21 May 2021 • Shengyi Huang, Santiago Ontañón, Chris Bamford, Lukasz Grela
In recent years, researchers have achieved great success in applying Deep Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games, creating strong autonomous agents that could defeat professional players in StarCraft~II.
no code implementations • 20 May 2021 • Sukhdeep S. Sodhi, Ellie Ka-In Chio, Ambarish Jash, Santiago Ontañón, Ajit Apte, Ankit Kumar, Ayooluwakunmi Jeje, Dima Kuzmin, Harry Fung, Heng-Tze Cheng, Jon Effrat, Tarush Bali, Nitin Jindal, Pei Cao, Sarvjeet Singh, Senqiang Zhou, Tameen Khan, Amol Wankhede, Moustafa Alzantot, Allen Wu, Tushar Chandra
As more and more online search queries come from voice, automatic speech recognition becomes a key component to deliver relevant search results.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
no code implementations • 2 Mar 2021 • Santiago Ontañón, Jichen Zhu
Personalized adaptation technology has been adopted in a wide range of digital applications such as health, training and education, e-commerce and entertainment.
Human-Computer Interaction
no code implementations • 15 Feb 2021 • Jichen Zhu, Santiago Ontañón
Computer games represent an ideal research domain for the next generation of personalized digital applications.
no code implementations • 10 Feb 2021 • Robert C. Gray, Jichen Zhu, Santiago Ontañón
This paper explores multi-armed bandit (MAB) strategies in very short horizon scenarios, i. e., when the bandit strategy is only allowed very few interactions with the environment.
no code implementations • 10 Feb 2021 • Robert C. Gray, Jichen Zhu, Dannielle Arigo, Evan Forman, Santiago Ontañón
This paper focuses on building personalized player models solely from player behavior in the context of adaptive games.
no code implementations • 25 Jan 2021 • Jichen Zhu, Diane H. Dallal, Robert C. Gray, Jennifer Villareale, Santiago Ontañón, Evan M. Forman, Danielle Arigo
In addition to design implications for social comparison features in social apps, this paper identified the personalization paradox, the conflict between user modeling and adaptation, as a key design challenge of personalized applications for behavior change.
2 code implementations • 5 Oct 2020 • Shengyi Huang, Santiago Ontañón
Training agents using Reinforcement Learning in games with sparse rewards is a challenging problem, since large amounts of exploration are required to retrieve even the first reward.
2 code implementations • 25 Jun 2020 • Shengyi Huang, Santiago Ontañón
In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games.
no code implementations • 18 Feb 2020 • Santiago Ontañón
The notions of distance and similarity play a key role in many machine learning approaches, and artificial intelligence (AI) in general, since they can serve as an organizing principle by which individuals classify objects, form concepts and make generalizations.
3 code implementations • 26 Oct 2019 • Shengyi Huang, Santiago Ontañón
This paper presents a preliminary study comparing different observation and action space representations for Deep Reinforcement Learning (DRL) in the context of Real-time Strategy (RTS) games.
no code implementations • 15 Aug 2019 • Pavan Kantharaju, Katelyn Alderfer, Jichen Zhu, Bruce Char, Brian Smith, Santiago Ontañón
This paper focuses on "tracing player knowledge" in educational games.
no code implementations • 4 Jul 2019 • Jichen Zhu, Santiago Ontañón
Experience Management studies AI systems that automatically adapt interactive experiences such as games to tailor to specific players and to fulfill design goals.
no code implementations • 13 Oct 2017 • Santiago Ontañón
Games with large branching factors pose a significant challenge for game tree search algorithms.
1 code implementation • 23 Jun 2016 • Adam James Summerville, Sam Snodgrass, Michael Mateas, Santiago Ontañón
Levels are a key component of many different video games, and a large body of work has been produced on how to procedurally generate game levels.
no code implementations • 17 May 2016 • Alberto Uriarte, Santiago Ontañón
This paper presents three forward models for two-player attrition games, which we call "combat models", and show how they can be used to simulate combat in RTS games.
1 code implementation • 23 Apr 2016 • Santiago Ontañón
This document provides the foundations behind the functionality provided by the $\rho$G library (https://github. com/santiontanon/RHOG), focusing on the basic operations the library provides: subsumption, refinement of directed labeled graphs, and distance/similarity assessment between directed labeled graphs.