Daniel Beechey
Research Scientist
Huawei Noah's Ark Lab, London, United Kingdom
I am a research scientist at Huawei Noah's Ark Lab. Previously, I was a PhD student as part of the Bath Reinforcement Learning Lab, supervised by Özgür Şimşek. I'm interested in all things reinforcement learning, particularly questioning the basic building blocks we use to study and create artificial intelligence.
News
- Jun. 2025: New paper: A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values.
- Jun. 2025: Joinined the AI Agent group at Huawei Noah's Ark Lab as a Research Scientist!
- Jun. 2025: Presented a poster at the 2025 Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM). Poster.
- Feb. 2025: Gave a talk as part of the ART-AI colloquium series. Slides.
- Oct. 2024: Presenting a poster at the 17th European Workshop on Reinforcement Learning (EWRL). Poster.
- Sep. 2024: Attended the Mediterranean Machine Learning Summer School. Poster.
- Jul. 2024: Attended the CIFAR Deep Learning + Reinforcement Learning (DLRL) Summer School. Poster.
- Jun. 2024: Accepted a Doctoral Recognition Award at the Bath Doctoral Research Celebration Evening!
- Jun. 2024: Gave a talk as part of the Digital Futures session at the Bath Doctoral Festival of Ideas. Poster.
- Apr. 2024: Gave a talk to the Bath AI Society on the work of the Bath Reinforcement Learning Lab.
- Oct. 2023: Attended the UKRI Inter AI CDT Conference in Bristol. Poster.
- Sep. 2023: Our work on "Reformulating Reactivity Design for Data-Efficient Machine Learning" has been accepted to ACS Catalysis!
- Aug. 2023: Presented our poster on "Explaining Reinforcement Learning with Shapley Values" at ICML 2023.
- Jul. 2023: Presented a talk on "Explaining Reinforcement Learning with Shapley Values" at the Bath Conference of Computer Science.
- Jun. 2023: Presented a talk on "Explaining Reinforcement Learning with Shapley Values" at the Alan Turing Institute Student Presentations.
- Apr. 2023: Our paper on "Explaining Reinforcement Learning with Shapley Values" has been accepted as a poster at ICML 2023!
- Oct. 2021: Joined the Bath Reinforcement Learning Lab at the University of Bath as a 1st year Ph.D. student.
Interests
Since the start of my PhD, I have been interested in identifying and explaining key aspects of artificial agents interacting with their environments: behaviour, performance and prediction. Recently, I have been using the lense of bounded rationality to explore how fundamental mechanisms of intelligence—such as representations, hierarchy and continual learning—naturally emerge as necessary conditions of resource-constrained agents. This has led me to question the philosophical foundations of reinforcement learning: what is an agent, and how do our assumptions shape the algorithms and conceptual models we design and build?
Papers
Talks
A Theoretical Framework for Explaining Reinforcement Learning with Shapley Values
ART-AI Colloquium Series, February 2024
Bath Doctoral Festival of Ideas, July 2024
An Introduction to Explainable and Hierarchical Reinforcement Learning
Bath AI Society, April 2024
Teaching
