Search Results for author:
Found 19 papers, 6 papers with code
ICED: Zero-Shot Transfer in Reinforcement Learning via In-Context Environment Design
ICED generates levels using a variational autoencoder 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.
Data-driven Prior Learning for Bayesian Optimisation
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.
Non-Compositionality in Sentiment: New Data and Analyses
When natural language phrases are combined, their meaning is often more than the sum of their parts.
Balancing utility and cognitive cost in social representation
To successfully navigate its environment, an agent must construct and maintain representations of the other agents that it encounters.
How the level sampling process impacts zero-shot generalisation in deep reinforcement learning
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.
DreamDecompiler: Bayesian Program Learning by Decompiling Amortised Knowledge
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.
Bayesian Optimisation Against Climate Change: Applications and Benchmarks
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.
Designing Optimal Behavioral Experiments Using Machine Learning
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.
Selective imitation on the basis of reward function similarity
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.
Causal Explanations for Sequential Decision-Making in Multi-Agent Systems
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.
Actively learning to learn causal relationships
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.
Can Transformer be Too Compositional? Analysing Idiom Processing in Neural Machine Translation
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.
Bayesian Optimisation for Active Monitoring of Air Pollution
Air pollution is one of the leading causes of mortality globally, resulting in millions of deaths each year.
Building Object-based Causal Programs for Human-like Generalization
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.
Bayesian Optimal Experimental Design for Simulator Models of Cognition
Bayesian optimal experimental design (BOED) is a methodology to identify experiments that are expected to yield informative data.
Optimising Placement of Pollution Sensors in Windy Environments
Air pollution is one of the most important causes of mortality in the world.
The Human Kernel
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.
A rational model of preference learning and choice prediction by children
Young children demonstrate the ability to make inferences about the preferences of other agents based on their choices.
