9

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
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 …
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 …
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, …
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 …
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, …
PDF Cite Project