1 code implementation • 20 Dec 2023 • William Hill, Ireton Liu, Anita de Mello Koch, Damion Harvey, Nishanth Kumar, George Konidaris, Steven James
We propose a new benchmark for planning tasks based on the Minecraft game.
no code implementations • 18 Dec 2023 • Tristan Bester, Benjamin Rosman, Steven James, Geraud Nangue Tasse
We present counting reward automata-a finite state machine variant capable of modelling any reward function expressible as a formal language.
2 code implementations • NeurIPS 2023 • Michael Beukman, Devon Jarvis, Richard Klein, Steven James, Benjamin Rosman
To this end, we introduce a neural network architecture, the Decision Adapter, which generates the weights of an adapter module and conditions the behaviour of an agent on the context information.
1 code implementation • 1 Jun 2023 • Muhammad U. Nasir, Sam Earle, Christopher Cleghorn, Steven James, Julian Togelius
By merging the code-generating abilities of LLMs with the diversity and robustness of QD solutions, we introduce \texttt{LLMatic}, a Neural Architecture Search (NAS) algorithm.
1 code implementation • 31 May 2023 • Geraud Nangue Tasse, Tamlin Love, Mark Nemecek, Steven James, Benjamin Rosman
A common solution is for a human expert to define either a penalty in the reward function or a cost to be minimised when reaching unsafe states.
1 code implementation • 3 Feb 2023 • Michael Beukman, Manuel Fokam, Marcel Kruger, Guy Axelrod, Muhammad Nasir, Branden Ingram, Benjamin Rosman, Steven James
Procedural content generation (PCG) is a growing field, with numerous applications in the video game industry and great potential to help create better games at a fraction of the cost of manual creation.
2 code implementations • 20 Oct 2022 • Muhammad Umair Nasir, Michael Beukman, Steven James, Christopher Wesley Cleghorn
In this work, we tackle the problem of open-ended learning by introducing a method that simultaneously evolves agents and increasingly challenging environments.
no code implementations • 29 Jul 2022 • Nicholas Muir, Steven James
We propose a framework to tackle the procedural content generation problem that combines the best of ES and RL.
no code implementations • 23 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.
no code implementations • 25 May 2022 • Geraud Nangue Tasse, Devon Jarvis, Steven James, Benjamin Rosman
The agent can then flexibly compose them both logically and temporally to provably achieve temporal logic specifications in any regular language, such as regular fragments of linear temporal logic.
no code implementations • 18 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.
no code implementations • 12 May 2022 • Nathan Michlo, Devon Jarvis, Richard Klein, Steven James
In this work, we investigate the properties of data that cause popular representation learning approaches to fail.
no code implementations • 4 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.
1 code implementation • 22 Apr 2022 • Michael Beukman, Michael Mitchley, Dean Wookey, Steven James, George Konidaris
We further demonstrate that a fixed wavelet basis set performs comparably against the high-performing Fourier basis on Mountain Car and Acrobot, and that the adaptive methods provide a convenient approach to addressing an oversized initial basis set, while demonstrating performance comparable to, or greater than, the fixed wavelet basis.
1 code implementation • 14 Apr 2022 • Michael Beukman, Christopher W Cleghorn, Steven James
Procedurally generated video game content has the potential to drastically reduce the content creation budget of game developers and large studios.
1 code implementation • 27 Feb 2022 • Nathan Michlo, Richard Klein, Steven James
Our findings demonstrate the subjective nature of disentanglement and the importance of considering the interaction between the ground-truth factors, data and notably, the reconstruction loss, which is under-recognised in the literature.
no code implementations • 1 Feb 2022 • Nishai Kooverjee, Steven James, Terence van Zyl
Graph neural networks (GNNs) build on the success of deep learning models by extending them for use in graph spaces.
1 code implementation • 25 Jan 2022 • Michael Beukman, Steven James, Christopher Cleghorn
With increasing interest in procedural content generation by academia and game developers alike, it is vital that different approaches can be compared fairly.
no code implementations • 9 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.
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.
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.
no code implementations • ICML Workshop LifelongML 2020 • Geraud Nangue Tasse, Steven James, Benjamin Rosman
The ability to produce novel behaviours from existing skills is an important property of lifelong learning agents.
no code implementations • 19 Jan 2020 • Matthew Cockcroft, Shahil Mawjee, Steven James, Pravesh Ranchod
We present a method for learning options from segmented demonstration trajectories.
1 code implementation • 14 Jan 2020 • Kimessha Paupamah, Steven James, Richard Klein
Deep neural networks are typically too computationally expensive to run in real-time on consumer-grade hardware and low-powered devices.
Ranked #1 on Neural Network Compression on CIFAR-10
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.
no code implementations • 2 Jan 2020 • Nishai Kooverjee, Steven James, Terence van Zyl
In this paper we analyse the effectiveness of using deep transfer learning for character recognition tasks.
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.
no code implementations • 12 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.