Robert Tracey
Robert Tracey has a total of 7 co-authors. Here are the top co-authors by number of shared publications:
- Lan Hoang
IBM Research Europe
2 shared publications - Clyde Fare
IBM Research Europe -UK Hartree Centre SciTech Daresbury Warrington WA4 4AD Cheshire UK
1 shared publication - Felix Subelet
Sci-Tech Daresbury
1 shared publication - George K. Holt
UK Atomic Energy Authority, Abingdon, United Kingdom
1 shared publication - Lamogha Chiazor
IBM Research, Hursley, Winchester, UK
1 shared publication - Michalis Smyrnakis
STFC Hartree Centre, Daresbury, United Kingdom
1 shared publication
Latest Publications
- Open Access
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (21) , 23787-23789
MANDREL: Modular Reinforcement Learning Pipelines for Material Discovery
AI-driven materials discovery is evolving rapidly with new approaches and pipelines for experimentation and design. However, the pipelines are often designed in isolation. We introduce a modular reinforcement learning framework for inter-operable experimentation and design of tailored, novel molecular species. The framework unifies reinforcement learning (RL) pipelines and allows the mixing and matching of choices for the underlying chemical action space, molecular representation, desired molecular properties, and RL algorithm. Our demo showcases the framework's capabilities applied to benchmark problems like quantitative estimate of drug-likeness and PLogP, as well as the design of novel small molecule solvents for carbon capture.
- 24 March 2024
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (21) , 23787-23789
Open AccessMANDREL: Modular Reinforcement Learning Pipelines for Material Discovery
AI-driven materials discovery is evolving rapidly with new approaches and pipelines for experimentation and design. However, the pipelines are often designed in isolation. We introduce a modular reinforcement learning framework for inter-operable experimentation and design of tailored, novel molecular species. The framework unifies reinforcement learning (RL) pipelines and allows the mixing and matching of choices for the underlying chemical action space, molecular representation, desired molecular properties, and RL algorithm. Our demo showcases the framework's capabilities applied to benchmark problems like quantitative estimate of drug-likeness and PLogP, as well as the design of novel small molecule solvents for carbon capture.
- 20 October 2020
- Published by Springer Nature
- p. 267-279
AI-Driven Holistic Approach to Energy Efficient HPC
- 20 October 2020
- Published by Springer Nature
- p. 267-279
AI-Driven Holistic Approach to Energy Efficient HPC