9

Just-in-Time Sparsity: Learning Dynamic Sparsity Schedules
Sparse neural networks have various computational benefits while often being able to maintain or improve the generalization performance …
PDF Cite
World Value Functions: Knowledge Representation for Learning and Planning
We propose world value functions (WVFs), a type of goaloriented general value function that represents how to solve not just a given …
PDF Cite Project
Analysing the Effects of Transfer Learning on Low-Resourced Named Entity Recognition Performance
Transfer learning has led to large gains in performance for nearly all NLP tasks while making downstream models easier and faster to …
PDF Cite
Effect of Tokenisation Strategies for Low-Resourced Southern African Languages
Research into machine translation for African languages is very limited and low- resourced in terms of datasets and model evaluations. …
PDF Cite
Generalisation in Lifelong Reinforcement Learning through Logical Composition
We leverage logical composition in reinforcement learning to create a framework that enables an agent to autonomously determine whether …
PDF Cite Project
The Challenge of Redundancy on Multi-Agent Value Factorisation
Recently there has been great development in the field of multi-agent reinforcement learning (MARL). In the cooperative partially …
PDF Cite
Should I Trust You? Incorporating Unreliable Expert Advice in Human-Agent Interaction
A major concern in reinforcement learning, especially as it is applied to real-world and robotics problems, is that of …
PDF Cite
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 …
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 …
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 …
PDF Cite Project