269 citations · 443 across the 19 of their papers we have counts for
21 papers
Multi-Task End-to-End Training Improves Conversational Recommendation
Naveen Ram, Dima Kuzmin, Ellie Ka In Chio +4
In this paper, we analyze the performance of a multitask end-to-end transformer model on the task of conversational recommendations, which aim to provide recommendations based on a…
LogicInference: A New Dataset for Teaching Logical Inference to seq2seq Models
Santiago Ontanon, Joshua Ainslie, Vaclav Cvicek +1
Machine learning models such as Transformers or LSTMs struggle with tasks that are compositional in nature such as those involving reasoning/inference. Although many datasets exist…
LongT5: Efficient Text-To-Text Transformer for Long Sequences
Mandy Guo, Joshua Ainslie, David Uthus +4
Recent work has shown that either (1) increasing the input length or (2) increasing model size can improve the performance of Transformer-based neural models. In this paper, we pre…
Gym-RTS: Toward Affordable Full Game Real-time Strategy Games Research with Deep Reinforcement Learning
Shengyi Huang, Santiago Ontañón, Chris Bamford +1
In recent years, researchers have achieved great success in applying Deep Reinforcement Learning (DRL) algorithms to Real-time Strategy (RTS) games, creating strong autonomous agen…
FNet: Mixing Tokens with Fourier Transforms
James Lee-Thorp, Joshua Ainslie, Ilya Eckstein +1
We show that Transformer encoder architectures can be sped up, with limited accuracy costs, by replacing the self-attention sublayers with simple linear transformations that "mix"…
Rotating Boson Stars Using Finite Differences and Global Newton Methods
Santiago Ontanon, Miguel Alcubierre
We study Rotating Boson Star initial data for Numerical Relativity as previously considered by Yoshida and Eriguchi, Lai (arXiv:gr-qc/0410040v2), and Grandclement, Somé and Gourgou…
Player-Centered AI for Automatic Game Personalization: Open Problems
Jichen Zhu, Santiago Ontañón
Computer games represent an ideal research domain for the next generation of personalized digital applications. This paper presents a player-centered framework of AI for game perso…
Personalization Paradox in Behavior Change Apps: Lessons from a Social Comparison-Based Personalized App for Physical Activity
Jichen Zhu, Diane H. Dallal, Robert C. Gray +4
Social comparison-based features are widely used in social computing apps. However, most existing apps are not grounded in social comparison theories and do not consider individual…
Player Modeling via Multi-Armed Bandits
Robert C. Gray, Jichen Zhu, Dannielle Arigo +2
This paper focuses on building personalized player models solely from player behavior in the context of adaptive games. We present two main contributions: The first is a novel appr…
Regression Oracles and Exploration Strategies for Short-Horizon Multi-Armed Bandits
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.…
Big Bird: Transformers for Longer Sequences
Manzil Zaheer, Guru Guruganesh, Avinava Dubey +8
Transformers-based models, such as BERT, have been one of the most successful deep learning models for NLP. Unfortunately, one of their core limitations is the quadratic dependency…
ETC: Encoding Long and Structured Inputs in Transformers
Joshua Ainslie, Santiago Ontanon, Chris Alberti +7
Transformer models have advanced the state of the art in many Natural Language Processing (NLP) tasks. In this paper, we present a new Transformer architecture, Extended Transforme…
Tracing Player Knowledge in a Parallel Programming Educational Game
Pavan Kantharaju, Katelyn Alderfer, Jichen Zhu +3
This paper focuses on "tracing player knowledge" in educational games. Specifically, given a set of concepts or skills required to master a game, the goal is to estimate the likeli…
Experience Management in Multi-player Games
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. Although it has b…
Combinatorial Multi-armed Bandits for Real-Time Strategy Games
Santiago Ontañón
Games with large branching factors pose a significant challenge for game tree search algorithms. In this paper, we address this problem with a sampling strategy for Monte Carlo Tre…
The VGLC: The Video Game Level Corpus
Adam James Summerville, Sam Snodgrass, Michael Mateas +1
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. Recently, Machine Learning techniq…
Combat Models for RTS Games
Alberto Uriarte, Santiago Ontañón
Game tree search algorithms, such as Monte Carlo Tree Search (MCTS), require access to a forward model (or "simulator") of the game at hand. However, in some games such forward mod…
RHOG: A Refinement-Operator Library for Directed Labeled Graphs
Santiago Ontañón
This document provides the foundations behind the functionality provided by the G library (https://github.com/santiontanon/RHOG), focusing on the basic operations the library pr…
A semantic network-based evolutionary algorithm for computational creativity
Atilim Gunes Baydin, Ramon Lopez de Mantaras, Santiago Ontanon
We introduce a novel evolutionary algorithm (EA) with a semantic network-based representation. For enabling this, we establish new formulations of EA variation operators, crossover…
Experiments with Game Tree Search in Real-Time Strategy Games
Santiago Ontanon
Game tree search algorithms such as minimax have been used with enormous success in turn-based adversarial games such as Chess or Checkers. However, such algorithms cannot be direc…
Automated Generation of Cross-Domain Analogies via Evolutionary Computation
Atilim Gunes Baydin, Ramon Lopez de Mantaras, Santiago Ontanon
Analogy plays an important role in creativity, and is extensively used in science as well as art. In this paper we introduce a technique for the automated generation of cross-domai…