1 code implementation • 11 Mar 2024 • Balint Gyevnar, Stephanie Droop, Tadeg Quillien, Shay B. Cohen, Neil R. Bramley, Christopher G. Lucas, Stefano V. Albrecht
Cognitive science can help us understand which explanations people might expect, and in which format they frame these explanations, whether causal, counterfactual, or teleological (i. e., purpose-oriented).
no code implementations • 5 Feb 2024 • Samuel Garcin, James Doran, Shangmin Guo, Christopher G. Lucas, Stefano V. Albrecht
DRED generates levels using a generative model trained over an initial set of level parameters, reducing distributional shift, and achieves significant improvements in ZSG over adaptive level sampling strategies and UED methods.
1 code implementation • 24 Nov 2023 • Sigrid Passano Hellan, Christopher G. Lucas, Nigel H. Goddard
We replace this assumption with a weaker one only requiring the shape of the optimisation landscape to be similar, and analyse the recent method Prior Learning for Bayesian Optimisation - PLeBO - in this setting.
1 code implementation • 31 Oct 2023 • Verna Dankers, Christopher G. Lucas
When natural language phrases are combined, their meaning is often more than the sum of their parts.
no code implementations • 7 Oct 2023 • Max Taylor-Davies, Christopher G. Lucas
To successfully navigate its environment, an agent must construct and maintain representations of the other agents that it encounters.
no code implementations • 5 Oct 2023 • Samuel Garcin, James Doran, Shangmin Guo, Christopher G. Lucas, Stefano V. Albrecht
A key limitation preventing the wider adoption of autonomous agents trained via deep reinforcement learning (RL) is their limited ability to generalise to new environments, even when these share similar characteristics with environments encountered during training.
no code implementations • 28 Aug 2023 • Jan-Philipp Fränken, Christopher G. Lucas, Neil R. Bramley, Steven T. Piantadosi
Infants expect physical objects to be rigid and persist through space and time and in spite of occlusion.
no code implementations • 13 Jun 2023 • Alessandro B. Palmarini, Christopher G. Lucas, N. Siddharth
The cost of search is amortised by training a neural search policy, reducing search breadth and effectively "compiling" useful information to compose program solutions across tasks.
1 code implementation • 7 Jun 2023 • Sigrid Passano Hellan, Christopher G. Lucas, Nigel H. Goddard
Bayesian optimisation is a powerful method for optimising black-box functions, popular in settings where the true function is expensive to evaluate and no gradient information is available.
no code implementations • 12 May 2023 • Max Taylor-Davies, Stephanie Droop, Christopher G. Lucas
Imitation is a key component of human social behavior, and is widely used by both children and adults as a way to navigate uncertain or unfamiliar situations.
1 code implementation • 12 May 2023 • Simon Valentin, Steven Kleinegesse, Neil R. Bramley, Peggy Seriès, Michael U. Gutmann, Christopher G. Lucas
As compared to experimental designs commonly used in the literature, we show that our optimal designs more efficiently determine which of a set of models best account for individual human behavior, and more efficiently characterize behavior given a preferred model.
1 code implementation • 21 Feb 2023 • Balint Gyevnar, Cheng Wang, Christopher G. Lucas, Shay B. Cohen, Stefano V. Albrecht
We present CEMA: Causal Explanations in Multi-Agent systems; a framework for creating causal natural language explanations of an agent's decisions in dynamic sequential multi-agent systems to build more trustworthy autonomous agents.
no code implementations • 20 Jun 2022 • Chentian Jiang, Christopher G. Lucas
We propose a hierarchical Bayesian model that goes beyond past models by predicting that people pursue information not only about the causal relationship at hand but also about causal overhypotheses$\unicode{x2014}$abstract beliefs about causal relationships that span multiple situations and constrain how we learn the specifics in each situation.
1 code implementation • ACL 2022 • Verna Dankers, Christopher G. Lucas, Ivan Titov
In this work, we investigate whether the non-compositionality of idioms is reflected in the mechanics of the dominant NMT model, Transformer, by analysing the hidden states and attention patterns for models with English as source language and one of seven European languages as target language.
no code implementations • 15 Feb 2022 • Sigrid Passano Hellan, Christopher G. Lucas, Nigel H. Goddard
Air pollution is one of the leading causes of mortality globally, resulting in millions of deaths each year.
no code implementations • 20 Nov 2021 • Bonan Zhao, Christopher G. Lucas, Neil R. Bramley
We present a novel task that measures how people generalize objects' causal powers based on observing a single (Experiment 1) or a few (Experiment 2) causal interactions between object pairs.
no code implementations • NeurIPS Workshop AI4Scien 2021 • Simon Valentin, Steven Kleinegesse, Neil R. Bramley, Michael U. Gutmann, Christopher G. Lucas
Bayesian optimal experimental design (BOED) is a methodology to identify experiments that are expected to yield informative data.
no code implementations • 19 Dec 2020 • Sigrid Passano Hellan, Christopher G. Lucas, Nigel H. Goddard
Air pollution is one of the most important causes of mortality in the world.
no code implementations • NeurIPS 2015 • Andrew Gordon Wilson, Christoph Dann, Christopher G. Lucas, Eric P. Xing
Bayesian nonparametric models, such as Gaussian processes, provide a compelling framework for automatic statistical modelling: these models have a high degree of flexibility, and automatically calibrated complexity.
no code implementations • NeurIPS 2008 • Christopher G. Lucas, Thomas L. Griffiths, Fei Xu, Christine Fawcett
Young children demonstrate the ability to make inferences about the preferences of other agents based on their choices.