188 citations · 219 across the 18 of their papers we have counts for
19 papers
DD-suite: A cross-platform package to build Decision Diagrams for optimization purposes
Antonia F. Blanco, Margarita Castro, Rodrigo Toro Icarte
Decision diagrams (DDs) have become a powerful tool for discrete optimization, supporting a wide range of algorithms that span cut-generation procedures, decomposition methods, and…
Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity
Cristian Hinostroza, Rodrigo Toro Icarte, Christ Devia +4
Large language models (LLMs) have revolutionized natural language processing. Understanding their internal mechanisms is crucial for developing more interpretable and optimized arc…
Seeing to Generalize: How Visual Data Corrects Binding Shortcuts
Nicolas Buzeta, Felipe del Rio, Cristian Hinostroza +3
Vision Language Models (VLMs) are designed to extend Large Language Models (LLMs) with visual capabilities, yet in this work we observe a surprising phenomenon: VLMs can outperform…
Extending NGU to Multi-Agent RL: A Preliminary Study
Juan Hernandez, Diego Fernández, Manuel Cifuentes +2
The Never Give Up (NGU) algorithm has proven effective in reinforcement learning tasks with sparse rewards by combining episodic novelty and intrinsic motivation. In this work, we…
Active Learning of Symbolic Automata Over Rational Numbers
Sebastian Hagedorn, Martín Muñoz, Cristian Riveros +1
Automata learning has many applications in artificial intelligence and software engineering. Central to these applications is the algorithm, introduced by Angluin. The …
Data Distributional Properties As Inductive Bias for Systematic Generalization
Felipe del Rio, Alain Raymond-Saez, Daniel Florea +4
Deep neural networks (DNNs) struggle at systematic generalization (SG). Several studies have evaluated the possibility to promote SG through the proposal of novel architectures, lo…
Being Considerate as a Pathway Towards Pluralistic Alignment for Agentic AI
Parand A. Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte +1
Pluralistic alignment is concerned with ensuring that an AI system's objectives and behaviors are in harmony with the diversity of human values and perspectives. In this paper we s…
Reward Machines for Deep RL in Noisy and Uncertain Environments
Andrew C. Li, Zizhao Chen, Toryn Q. Klassen +3
Reward Machines provide an automaton-inspired structure for specifying instructions, safety constraints, and other temporally extended reward-worthy behaviour. By exposing the unde…
Learning Symbolic Representations for Reinforcement Learning of Non-Markovian Behavior
Phillip J. K. Christoffersen, Andrew C. Li, Rodrigo Toro Icarte +1
Many real-world reinforcement learning (RL) problems necessitate learning complex, temporally extended behavior that may only receive reward signal when the behavior is completed.…
Noisy Symbolic Abstractions for Deep RL: A case study with Reward Machines
Andrew C. Li, Zizhao Chen, Pashootan Vaezipoor +3
Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward func…
Challenges to Solving Combinatorially Hard Long-Horizon Deep RL Tasks
Andrew C. Li, Pashootan Vaezipoor, Rodrigo Toro Icarte +1
Deep reinforcement learning has shown promise in discrete domains requiring complex reasoning, including games such as Chess, Go, and Hanabi. However, this type of reasoning is les…
Learning Reward Machines: A Study in Partially Observable Reinforcement Learning
Rodrigo Toro Icarte, Ethan Waldie, Toryn Q. Klassen +3
Reinforcement learning (RL) is a central problem in artificial intelligence. This problem consists of defining artificial agents that can learn optimal behaviour by interacting wit…
AppBuddy: Learning to Accomplish Tasks in Mobile Apps via Reinforcement Learning
Maayan Shvo, Zhiming Hu, Rodrigo Toro Icarte +3
Human beings, even small children, quickly become adept at figuring out how to use applications on their mobile devices. Learning to use a new app is often achieved via trial-and-e…
Be Considerate: Objectives, Side Effects, and Deciding How to Act
Parand Alizadeh Alamdari, Toryn Q. Klassen, Rodrigo Toro Icarte +1
Recent work in AI safety has highlighted that in sequential decision making, objectives are often underspecified or incomplete. This gives discretion to the acting agent to realize…
LTL2Action: Generalizing LTL Instructions for Multi-Task RL
Pashootan Vaezipoor, Andrew Li, Rodrigo Toro Icarte +1
We address the problem of teaching a deep reinforcement learning (RL) agent to follow instructions in multi-task environments. Instructions are expressed in a well-known formal lan…
Interpretable Sequence Classification via Discrete Optimization
Maayan Shvo, Andrew C. Li, Rodrigo Toro Icarte +1
Sequence classification is the task of predicting a class label given a sequence of observations. In many applications such as healthcare monitoring or intrusion detection, early c…
The act of remembering: a study in partially observable reinforcement learning
Rodrigo Toro Icarte, Richard Valenzano, Toryn Q. Klassen +3
Reinforcement Learning (RL) agents typically learn memoryless policies---policies that only consider the last observation when selecting actions. Learning memoryless policies is ef…
Reward Machines: Exploiting Reward Function Structure in Reinforcement Learning
Rodrigo Toro Icarte, Toryn Q. Klassen, Richard Valenzano +1
Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover reward…
How a General-Purpose Commonsense Ontology can Improve Performance of Learning-Based Image Retrieval
Rodrigo Toro Icarte, Jorge A. Baier, Cristian Ruz +1
The knowledge representation community has built general-purpose ontologies which contain large amounts of commonsense knowledge over relevant aspects of the world, including usefu…