400 citations · 412 across the 11 of their papers we have counts for
12 papers
A2C is a special case of PPO
Shengyi Huang, Anssi Kanervisto, Antonin Raffin +3
Advantage Actor-critic (A2C) and Proximal Policy Optimization (PPO) are popular deep reinforcement learning algorithms used for game AI in recent years. A common understanding is t…
Identifying On-road Scenarios Predictive of ADHD usingDriving Simulator Time Series Data
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…
Iterative Decoding for Compositional Generalization in Transformers
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. I…
Making Transformers Solve Compositional Tasks
Santiago Ontañón, Joshua Ainslie, Vaclav Cvicek +1
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. In this pa…
Improving Compositional Generalization in Classification Tasks via Structure Annotations
Juyong Kim, Pradeep Ravikumar, Joshua Ainslie +1
Compositional generalization is the ability to generalize systematically to a new data distribution by combining known components. Although humans seem to have a great ability to g…
Mondegreen: A Post-Processing Solution to Speech Recognition Error Correction for Voice Search Queries
Sukhdeep S. Sodhi, Ellie Ka-In Chio, Ambarish Jash +18
As more and more online search queries come from voice, automatic speech recognition becomes a key component to deliver relevant search results. Errors introduced by automatic spee…
The Personalization Paradox: the Conflict between Accurate User Models and Personalized Adaptive Systems
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. Personalization sy…
Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-time Strategy Games
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 rewar…
A Closer Look at Invalid Action Masking in Policy Gradient Algorithms
Shengyi Huang, Santiago Ontañón
In recent years, Deep Reinforcement Learning (DRL) algorithms have achieved state-of-the-art performance in many challenging strategy games. Because these games have complicated ru…
Understanding Learners' Problem-Solving Strategies in Concurrent and Parallel Programming: A Game-Based Approach
Jichen Zhu, Katelyn Alderfer, Brian Smith +2
Concurrent and parallel programming (CPP) is an increasingly important subject in Computer Science Education. However, the conceptual shift from sequential programming is notorious…
An Overview of Distance and Similarity Functions for Structured Data
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 princ…
Comparing Observation and Action Representations for Deep Reinforcement Learning in RTS
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…