Edward Hughes

Edward Hughes

Auto-generated profile, based on publicly available information

Edward Hughes

Google DeepMind, London, UK

Research Focus & Metrics

Academic Career Length

26Years (2001-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
12 November 2025 in Nature
Verified
Journal Article
Open access
PDF file
THThomas Hubert
Thomas Hubert
RMRishi Mehta
Rishi Mehta
LSLaurent Sartran
Laurent Sartran
MHMiklós Z. Horváth
Miklós Z. Horváth
GŽGoran Žužić
Goran Žužić
DSDavid Silver
David Silver
A long-standing goal of artificial intelligence (AI) is to build systems capable of complex reasoning in vast domains, a task epitomized by mathematics with its boundless concepts and demand for rigorous proof. Recent AI systems, often reliant on human data, typically lack the formal verification necessary to guarantee correctness. By contrast, formal languages such as Lean 1 offer an interactive environment that grounds reasoning, and reinforcement learning (RL) provides a mechanism for learning in such environments. Here we present AlphaProof, an AlphaZero-inspired 2 agent that learns to find formal proofs through RL by training on millions of auto-formalized problems. For the most difficult problems, it uses test-time RL, a method of generating and learning from millions of related problem variants at inference time to enable deep, problem-specific adaptation. AlphaProof substantially improves state-of-the-art results on historical mathematics competition problems. At the 2024 International Mathematical Olympiad competition, our AI system, with AlphaProof as its core reasoning engine, solved three out of the five non-geometry problems, including the competition’s most difficult problem. Combined with AlphaGeometry 2 3 , this performance, achieved with multi-day computation, resulted in reaching a score equivalent to that of a silver medallist, marking the first time an AI system achieved any medal-level performance, to our knowledge. Our work demonstrates that learning at scale from grounded experience produces agents with complex mathematical reasoning strategies, paving the way for a reliable AI tool in complex mathematical problem solving.

1 November 2020 in Artificial Intelligence
Verified
Journal Article
Closed access
YBYoram Bachrach
Yoram Bachrach
RERichard Everett
Richard Everett
EHEdward Hughes
Edward Hughes
ALAngeliki Lazaridou
Angeliki Lazaridou
JLJoel Z. Leibo
Joel Z. Leibo
TGThore Graepel
Thore Graepel

28 November 2023 in Nature Communications
Verified
Journal Article
Open access
PDF file
ABAvishkar Bhoopchand
Avishkar Bhoopchand
BBBethanie Brownfield
Bethanie Brownfield
ACAdrian Collister
Adrian Collister
ALAgustin Dal Lago
Agustin Dal Lago
AEAshley Edwards
Ashley Edwards
LZLei M. Zhang
Lei M. Zhang
Cultural transmission is the domain-general social skill that allows agents to acquire and use information from each other in real-time with high fidelity and recall. It can be thought of as the process that perpetuates fit variants in cultural evolution. In humans, cultural evolution has led to the accumulation and refinement of skills, tools and knowledge across generations. We provide a method for generating cultural transmission in artificially intelligent agents, in the form of few-shot imitation. Our agents succeed at real-time imitation of a human in novel contexts without using any pre-collected human data. We identify a surprisingly simple set of ingredients sufficient for generating cultural transmission and develop an evaluation methodology for rigorously assessing it. This paves the way for cultural evolution to play an algorithmic role in the development of artificial general intelligence.

6 December 2019 in arXiv
Verified
Preprint
Open access
PDF file
NBNolan Bard
Nolan Bard
JFJakob N. Foerster
Jakob N. Foerster
SCSarath Chandar
Sarath Chandar
NBNeil Burch
Neil Burch
MLMarc Lanctot
Marc Lanctot
MBMichael Bowling
Michael Bowling
From the early days of computing, games have been important testbeds for studying how well machines can do sophisticated decision making. In recent years, machine learning has made dramatic advances with artificial agents reaching superhuman performance in challenge domains like Go, Atari, and some variants of poker. As with their predecessors of chess, checkers, and backgammon, these game domains have driven research by providing sophisticated yet well-defined challenges for artificial intelligence practitioners. We continue this tradition by proposing the game of Hanabi as a new challenge domain with novel problems that arise from its combination of purely cooperative gameplay with two to five players and imperfect information. In particular, we argue that Hanabi elevates reasoning about the beliefs and intentions of other agents to the foreground. We believe developing novel techniques for such theory of mind reasoning will not only be crucial for success in Hanabi, but also in broader collaborative efforts, especially those with human partners. To facilitate future research, we introduce the open-source Hanabi Learning Environment, propose an experimental framework for the research community to evaluate algorithmic advances, and assess the performance of current state-of-the-art techniques.

11 March 2019 in arXiv
Verified
Preprint
Open access
PDF file
JWJane X. Wang
Jane X. Wang
EHEdward Hughes
Edward Hughes
CFChrisantha Fernando
Chrisantha Fernando
WCWojciech M. Czarnecki
Wojciech M. Czarnecki
EDEdgar A. Duenez-Guzman
Edgar A. Duenez-Guzman
JLJoel Z. Leibo
Joel Z. Leibo
Multi-agent cooperation is an important feature of the natural world. Many tasks involve individual incentives that are misaligned with the common good, yet a wide range of organisms from bacteria to insects and humans are able to overcome their differences and collaborate. Therefore, the emergence of cooperative behavior amongst self-interested individuals is an important question for the fields of multi-agent reinforcement learning (MARL) and evolutionary theory. Here, we study a particular class of multi-agent problems called intertemporal social dilemmas (ISDs), where the conflict between the individual and the group is particularly sharp. By combining MARL with appropriately structured natural selection, we demonstrate that individual inductive biases for cooperation can be learned in a model-free way. To achieve this, we introduce an innovative modular architecture for deep reinforcement learning agents which supports multi-level selection. We present results in two challenging environments, and interpret these in the context of cultural and ecological evolution.

3 March 2019 in arXiv
Verified
Preprint
Open access
PDF file
JLJoel Z. Leibo
Joel Z. Leibo
JPJulien Perolat
Julien Perolat
EHEdward Hughes
Edward Hughes
SWSteven Wheelwright
Steven Wheelwright
AMAdam H. Marblestone
Adam H. Marblestone
TGThore Graepel
Thore Graepel
Here we explore a new algorithmic framework for multi-agent reinforcement learning, called Malthusian reinforcement learning, which extends self-play to include fitness-linked population size dynamics that drive ongoing innovation. In Malthusian RL, increases in a subpopulation's average return drive subsequent increases in its size, just as Thomas Malthus argued in 1798 was the relationship between preindustrial income levels and population growth. Malthusian reinforcement learning harnesses the competitive pressures arising from growing and shrinking population size to drive agents to explore regions of state and policy spaces that they could not otherwise reach. Furthermore, in environments where there are potential gains from specialization and division of labor, we show that Malthusian reinforcement learning is better positioned to take advantage of such synergies than algorithms based on self-play.