Sign in to your account

Steve James

Hi all

We'll be hosting an IndabaX event this Friday (17 September) that includes talks and tutorials with a focus on artificial intelligence and machine learning. Please see the information below and visit https://indabax.co.za/ for more info on this and other upcoming events.

Reinforcement learning, computer vision and AGI!


RAIL Lab and PRIME are co-hosting an IndabaX South Africa Roadshow event and you are cordially invited to join us! RAIL Lab and PRIME are two machine learning research groups from the Computer Science and Applied Math (CSAM / "kazam!") department at the University of the Witwatersrand.

RAIL Lab focuses primarily on learning in autonomous systems. In particular, we are interested in the acquisition of behaviours, as well as knowledge about the environment around a learning system. Our work draws on tools from multiple fields including decision theory, machine learning, and computer vision, using techniques including reinforcement learning, Bayesian models, deep neural networks, and Monte Carlo tree search.

The PRIME Lab is focused on problems in deep learning for computer vision, representation learning, and learning in situations where data and labels are scarce. We have projects based on computer vision, natural language processing, self-supervised and weakly-supervised learning, generative modelling, and latent space analysis; as well as in energy, education, and healthcare.


When: 17 Sept 2021 from 14h00 - 17h00 SAST (convert to your...

Steve James

Applications are open for a full-time postdoctoral research position in reinforcement learning for robotics, at the RAIL laboratory at the University of the Witwatersrand, Johannesburg, South Africa (https://www.raillab.org/).

This particular post will focus on behaviour composition and symbolic abstraction in reinforcement learning, specifically in extending our existing work to apply to flexible manipulation tasks on a two-armed manipulator robot.

The post is available from January 2022, for a period of 2-5 years. The candidate must have completed a PhD in the last 5 years, and have research experience in either reinforcement learning or robotics, preferably both.

Please submit your application using the online form https://forms.gle/oXdTHpg3QHni3M2W7 This will require a detailed CV, a motivation letter, two examples of your publications/written work, and two academic references.

The closing date for applications is 31 August 2021.

Enquiries can be sent to Prof. Benjamin Rosman (benjamin.rosman1@wits.ac.za).

Steve James

Apply for a DeepMind Scholarship for an MSc at the University of the Witwatersrand!

Applications are now open to anyone from Africa who wishes to pursue a research- or coursework-based Masters at the University of the Witwatersrand in South Africa. The degrees are full-time, starting in January 2022, with a research focus on machine learning.

We are looking for candidates with strong backgrounds including experience with multivariate calculus, linear algebra, statistics, optimisation, and programming. Preference will be given to applicants from groups across the continent that are underrepresented in the global machine learning landscape.

Come and join our exciting multidisciplinary research team pushing the frontiers of fundamental machine learning research!

Apply here now: https://forms.gle/uC2rRJM12k5WsmWb7

Closing date for applications: 10 August 2021

Short-listed and unsuccessful applications will be notified by 31 August 2021.

Enquiries: Prof Benjamin Rosman (Benjamin.Rosman1@wits.ac.za)

Geraud Nangue Tasse

Abstract

In this work, we investigate how to compose learned skills to solve their conjunction, disjunction, and negation in a manner that is both principled and optimal. We begin by introducing a goal-oriented value function that amortises the learning effort over future tasks. We then prove that by composing these value functions in specific ways, we immediately recover the optimal policies for the conjunction, disjunction, and negation of learned tasks. Finally, we formalise the logical composition of tasks in a Boolean algebra structure. This gives us a notion of base tasks which when learned, can be composed to solve any other task in a domain.

Introduction

In this post, we are interested in answering the following question: given a set of existing skills, can we compose them to solve any task that is a logical combination of learned ones? To illustrate want we want, we will use the 2d video game domain of Van Niekerk [2019] where we train an agent to collect blue objects and separately train it to collect squares. We then see if we can obtain the skill to collect blue squares by averaging the learned value functions (since averaging is the best we can do from previous works [Haarnoja 2018, Van Niekerk 2019]). The respective value functions and trajectories are illustrated below.

Attempting to collect blue squares by composing learned skills - collecting blue objects and collecting squares - results in an agent that gets stuck optimally.

We can see that...