Search Results for author: Benjamin Rosman

Found 30 papers, 2 papers with code

Reinforcement Learning in Education: A Multi-Armed Bandit Approach

no code implementations1 Nov 2022 Herkulaas Combrink, Vukosi Marivate, Benjamin Rosman

Advances in reinforcement learning research have demonstrated the ways in which different agent-based models can learn how to optimally perform a task within a given environment.

online learning reinforcement-learning

A Framework for Undergraduate Data Collection Strategies for Student Support Recommendation Systems in Higher Education

no code implementations16 Oct 2022 Herkulaas MvE Combrink, Vukosi Marivate, Benjamin Rosman

While much effort and detail has gone into the expansion of explaining algorithmic decision making in this context, there is still a need to develop data collection strategies Therefore, the purpose of this paper is to outline a data collection framework specific to recommender systems within this context in order to reduce collection biases, understand student characteristics, and find an ideal way to infer optimal influences on the student journey.

Decision Making Recommendation Systems

World Value Functions: Knowledge Representation for Learning and Planning

no code implementations23 Jun 2022 Geraud Nangue Tasse, Benjamin Rosman, Steven James

We propose world value functions (WVFs), a type of goal-oriented general value function that represents how to solve not just a given task, but any other goal-reaching task in an agent's environment.

Skill Machines: Temporal Logic Composition in Reinforcement Learning

no code implementations25 May 2022 Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman

We introduce skill machines, a representation that can be learned directly from these reward machines that encode the solution to such tasks.


World Value Functions: Knowledge Representation for Multitask Reinforcement Learning

no code implementations18 May 2022 Geraud Nangue Tasse, Steven James, Benjamin Rosman

In this work we propose world value functions (WVFs), which are a type of general value function with mastery of the world - they represent not only how to solve a given task, but also how to solve any other goal-reaching task.


Learning Abstract and Transferable Representations for Planning

no code implementations4 May 2022 Steven James, Benjamin Rosman, George Konidaris

We propose a framework for autonomously learning state abstractions of an agent's environment, given a set of skills.

Learning to Follow Language Instructions with Compositional Policies

no code implementations9 Oct 2021 Vanya Cohen, Geraud Nangue Tasse, Nakul Gopalan, Steven James, Matthew Gombolay, Benjamin Rosman

We propose a framework that learns to execute natural language instructions in an environment consisting of goal-reaching tasks that share components of their task descriptions.

Generalisation in Lifelong Reinforcement Learning through Logical Composition

no code implementations ICLR 2022 Geraud Nangue Tasse, Steven James, Benjamin Rosman

We leverage logical composition in reinforcement learning to create a framework that enables an agent to autonomously determine whether a new task can be immediately solved using its existing abilities, or whether a task-specific skill should be learned.

reinforcement-learning Transfer Learning

Keep the Gradients Flowing: Using Gradient Flow to Study Sparse Network Optimization

no code implementations2 Feb 2021 Kale-ab Tessera, Sara Hooker, Benjamin Rosman

Based upon these findings, we show that gradient flow in sparse networks can be improved by reconsidering aspects of the architecture design and the training regime.

Autonomous Learning of Object-Centric Abstractions for High-Level Planning

no code implementations ICLR 2022 Steven James, Benjamin Rosman, George Konidaris

Such representations can immediately be transferred between tasks that share the same types of objects, resulting in agents that require fewer samples to learn a model of a new task.

Online Constrained Model-based Reinforcement Learning

no code implementations7 Apr 2020 Benjamin van Niekerk, Andreas Damianou, Benjamin Rosman

The environment's dynamics are learned from limited training data and can be reused in new task instances without retraining.

Gaussian Processes Model-based Reinforcement Learning +2

A Boolean Task Algebra for Reinforcement Learning

1 code implementation NeurIPS 2020 Geraud Nangue Tasse, Steven James, Benjamin Rosman

The ability to compose learned skills to solve new tasks is an important property of lifelong-learning agents.


If dropout limits trainable depth, does critical initialisation still matter? A large-scale statistical analysis on ReLU networks

no code implementations13 Oct 2019 Arnu Pretorius, Elan van Biljon, Benjamin van Niekerk, Ryan Eloff, Matthew Reynard, Steve James, Benjamin Rosman, Herman Kamper, Steve Kroon

Our results therefore suggest that, in the shallow-to-moderate depth setting, critical initialisation provides zero performance gains when compared to off-critical initialisations and that searching for off-critical initialisations that might improve training speed or generalisation, is likely to be a fruitless endeavour.

Using Objective Bayesian Methods to Determine the Optimal Degree of Curvature within the Loss Landscape

no code implementations25 Sep 2019 Devon Jarvis, Richard Klein, Benjamin Rosman

The efficacy of the width of the basin of attraction surrounding a minimum in parameter space as an indicator for the generalizability of a model parametrization is a point of contention surrounding the training of artificial neural networks, with the dominant view being that wider areas in the landscape reflect better generalizability by the trained model.

Estimation of Body Mass Index from Photographs using Deep Convolutional Neural Networks

no code implementations29 Aug 2019 Adam Pantanowitz, Emmanuel Cohen, Philippe Gradidge, Nigel Crowther, Vered Aharonson, Benjamin Rosman, David M Rubin

Obesity is an important concern in public health, and Body Mass Index is one of the useful (and proliferant) measures.

Learning Portable Representations for High-Level Planning

no code implementations ICML 2020 Steven James, Benjamin Rosman, George Konidaris

We present a framework for autonomously learning a portable representation that describes a collection of low-level continuous environments.

Transfer Learning for Prosthetics Using Imitation Learning

1 code implementation15 Jan 2019 Montaser Mohammedalamen, Waleed D. Khamies, Benjamin Rosman

In this paper, We Apply Reinforcement learning (RL) techniques to train a realistic biomechanical model to work with different people and on different walking environments.

Imitation Learning Transfer Learning

Zero-Shot Transfer with Deictic Object-Oriented Representation in Reinforcement Learning

no code implementations NeurIPS 2018 Ofir Marom, Benjamin Rosman

Object-oriented representations in reinforcement learning have shown promise in transfer learning, with previous research introducing a propositional object-oriented framework that has provably efficient learning bounds with respect to sample complexity.

reinforcement-learning Transfer Learning

Will it Blend? Composing Value Functions in Reinforcement Learning

no code implementations12 Jul 2018 Benjamin van Niekerk, Steven James, Adam Earle, Benjamin Rosman

An important property for lifelong-learning agents is the ability to combine existing skills to solve unseen tasks.


Symbol Emergence in Cognitive Developmental Systems: a Survey

no code implementations26 Jan 2018 Tadahiro Taniguchi, Emre Ugur, Matej Hoffmann, Lorenzo Jamone, Takayuki Nagai, Benjamin Rosman, Toshihiko Matsuka, Naoto Iwahashi, Erhan Oztop, Justus Piater, Florentin Wörgötter

However, the symbol grounding problem was originally posed to connect symbolic AI and sensorimotor information and did not consider many interdisciplinary phenomena in human communication and dynamic symbol systems in our society, which semiotics considered.

Reasoning about Unforeseen Possibilities During Policy Learning

no code implementations10 Jan 2018 Craig Innes, Alex Lascarides, Stefano V. Albrecht, Subramanian Ramamoorthy, Benjamin Rosman

Methods for learning optimal policies in autonomous agents often assume that the way the domain is conceptualised---its possible states and actions and their causal structure---is known in advance and does not change during learning.

Hierarchical Subtask Discovery With Non-Negative Matrix Factorization

no code implementations ICLR 2018 Adam C. Earle, Andrew M. Saxe, Benjamin Rosman

Hierarchical reinforcement learning methods offer a powerful means of planning flexible behavior in complicated domains.

Hierarchical Reinforcement Learning

Bayesian Policy Reuse

no code implementations1 May 2015 Benjamin Rosman, Majd Hawasly, Subramanian Ramamoorthy

We formalise the problem of policy reuse, and present an algorithm for efficiently responding to a novel task instance by reusing a policy from the library of existing policies, where the choice is based on observed 'signals' which correlate to policy performance.

Bayesian Optimisation

Clustering Markov Decision Processes For Continual Transfer

no code implementations15 Nov 2013 M. M. Hassan Mahmud, Majd Hawasly, Benjamin Rosman, Subramanian Ramamoorthy

The source subset forms an `$\epsilon$-net' over the original set of MDPs, in the sense that for each previous MDP $M_p$, there is a source $M^s$ whose optimal policy has $<\epsilon$ regret in $M_p$.

Transfer Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.