Home
Projects
Publications
People
Join the Lab
Contact
Login
9
Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization
Training sparse networks to converge to the same performance as dense neural architectures has proven to be elusive. Recent work …
Kale-ab Tessera
,
Sara Hooker
,
Benjamin Rosman
PDF
Cite
Logical Composition for Lifelong Reinforcement Learning
The ability to produce novel behaviours from existing skills is an important property of lifelong-learning agents. We build on recent …
Geraud Nangue Tasse
,
Steven James
,
Benjamin Rosman
PDF
Cite
Project
Learning Object-Centric Representations for High-Level Planning in Minecraft
We propose a method for autonomously learning an object-centric representation of a highdimensional environment that is suitable for …
Steven James
,
Benjamin Rosman
,
George Konidaris
PDF
Cite
Project
A Boolean Task Algebra for Reinforcement Learning
We propose a framework for defining a Boolean algebra over the space of tasks. This allows us to formulate new tasks in terms of the …
Geraud Nangue Tasse
,
Steven James
,
Benjamin Rosman
PDF
Cite
Project
Learning to Plan with Portable Symbols
We present a framework for autonomously learning a portable symbolic representation that describes a collection of low-level continuous …
Steven James
,
Benjamin Rosman
,
George Konidaris
PDF
Cite
Project
Will it Blend? Composing Value Functions in Reinforcement Learning
An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks. In general, …
Benjamin van Niekerk
,
Steven James
,
Adam Earle
,
Benjamin Rosman
PDF
Cite
Project
Learning the Influence Structure between Partially Observed Stochastic Processes using IoT Sensor Data
The recent widespread of availability of sensors, as part of the IoT, presents the opportunity to learn the properties of compound …
Ritesh Ajoodha
,
Benjamin Rosman
PDF
Cite
Hierarchical Subtask Discovery with Non-negative Matrix Factorization
Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains. However, …
Adam Earle
,
Andrew Saxe
,
Benjamin Rosman
PDF
Cite
Project
Toward Integrating Theory of Mind into Adaptive Decision-Making of Social Robots to Understand Human Intention
We propose an architecture that integrates Theory of Mind into a robot’s decision-making to infer a human’s intention and …
Orhan Can Görür
,
Benjamin Rosman
,
Guy Hoffman
,
Sahin Albayrak
PDF
Cite
An Investigation into the Effectiveness of Heavy Rollouts in UCT
Monte Carlo Tree Search (MCTS) is a family of directed search algorithms that has gained widespread attention in recent years, with its …
Steven James
,
Benjamin Rosman
,
George Konidaris
PDF
Cite
«
»
Cite
×