Supervision

2024–2025

Akshaya Jeyaramsankar MSc Data Science
Skill Discovery in Reinforcement Learning: Compartive Study of Option-Critic Methods

Calum Ogilvy MSc Computer Science
The Imitation-Performance Paradox: Distilling Robust and Interpretable Policies from Deep Reinforcement Learning Agents

Cameron Archibold MComp Computer Science and Artificial Intelligence, Year 4
Fully Closed-Loop Blood Glucose Control for Patients with Type 1 Diabetes using Deep Reinforcement Learning

Ellie Smyth MSc Data Science
Applications of Reinforcement Learning in Formula 1 Strategy

Farahmand Zeidaabadi Nezhad BSc Computer Science and Artificial Intelligence
Leveraging Pre-trained Vision-language Models to Train Generalisable Artificial Agents

George Rawlinson BSc Computer Science
Exploring the Application and Benefits of Hierarchical Networks

Harvey Ayling MComp Computer Science and Artificial Intelligence, Year 4
Applying Graph-Based Reinforcement Learning to Continuous-State Environments

Jamal Akhras MComp Computer Science and Artificial Intelligence, Year 4
Reinforcement Learning with Adversarial Motion Priors for Surface EMG-Driven Prosthetic Hand Control

Lara Sheard MComp Computer Science and Artificial Intelligence, Year 3
Skill Discovery within Multi-Agent Reinforcement Learning (MARL)

Xiaotong Bai MSc Computer Science
Emergence of Grammatical Structures from Multi-Agent Interactions in Referential Games

Yuxuan 'Tony' Zhang MComp Computer Science, Year 4
Pre-Training Option Critic

2023–2024

Andrej Lukic MSc Artificial Intelligence
Reducing Energy Consumption of an Embedded Forecasting System by Using Reinforcement Learning

Arnau Ayerbe Garcia MComp Computer Science, Year 4
Towards AGI, Preference Modelling and Alignment in LLMs: A Survey

Benedict Ellett BSc Computer Science
Use of Reinforcement Learning in Assembly Line Design

Henry Cunnison MSc Artificial Intelligence
Extending Generative Experience Replay in Online Reinforcement Learning

Jamal Akhras MComp Computer Science and Artificial Intelligence, Year 3
Using Proximal Policy Optimization with Adversarial Motion Priors to Aid Rehabilitation

Nathan Petrou BSc Computer Science
Unveiling the Impact: Exploring Key Parameters of Domain Randomization for Reinforcement Learning Agents

Pedro Jardim MSc Artificial Intelligence
In-Depth Analysis of FeUdal Networks

Shivam Sethi BSc Computer Science and Artificial Intelligence
The Generalisability of Cooperative Multi-Agent Reinforcement Learning Algorithms in a Mixed Setting

Yuxuan 'Tony' Zhang MComp Computer Science, Year 3
Towards Better Multi-Agent Hierarchical Reinforcement Learning: A Comparative Study on 'Overcooked!'

2022–2023

Andrea Zerio MSc Artificial Intelligence
PPDT: Learning Input-Dependent Prompts To Improve Few-Shot Policy Generalisation

Balamurali Chandran MSc Artificial Intelligence
Evaluation of Reinforcement Learning Algorithms for Job Scheduling in Dynamic Environments

Geoffrey Nightingale MSc Artificial Intelligence
Role Specialisation in Heterogeneous Agents Using Reinforcement Learning

Jorge Costa da Silva MSc Computer Science
Do reinforcement learning agents really learn?

Joseph Ballan MSc Artificial Intelligence
Developing Dynamic and Hybrid Personalized Recommendation Systems Using Deep Reinforcement Learning

Kavish Bolaky MSc Artificial Intelligence
Training a Competitive Racing Driver with Difficulty Adjustment using Deep Reinforcement Learning

Scarllette Ellis MComp Computer Science, Year 4
Getting Prepared: Finding Subgoals by using the Graphical Structure of Environments to Maximise Empowerment

Soledad 'Sole' Traverso MSc Artificial Intelligence
Learning Skills from Time-Based Representations: A Comparison between Graph Laplacian Representations and Successor Representations in Environments with Directed Graphs

Tran 'Danny' Quang Duy MSc Artificial Intelligence
An Analytical Attempt of Reinforcement Learning Techniques in the Game 2048

2021–2022

Dougal Houston BSc Computer Science
Reinforcement Learning on Ludo

Scarllette Ellis MComp Computer Science, Year 3
Reinforcement Learning in the Board Game Pandemic