Keynotes

Francesca Dominici

Co-Director of the Harvard Data Science Initiative, Harvard University

How much evidence do you need? Data Science to Inform Environmental and Climate Change Policy During the COVID-19 Pandemic

In this talk, I will provide an overview of data science methods, including methods for Bayesian analysis, causal inference, and machine learning, to inform environmental policy. This is based on my work analyzing a data platform of unprecedented size and representativeness. The platform includes more than 500 million observations on the health experience of over 95% of the US population older than 65 years old linked to air pollution exposure and several confounders. I will provide an overview of studies on air pollution exposure, environmental racism, wildfires, and how they also can exacerbate the vulnerability to COVID-19.

Press Coverage

Biography
Francesca Dominici, PhD is the co-Director of the Harvard Data Science Initiative, at Harvard University and the Clarence James Gamble Professor of Biostatistics, Population and Data Science at the Harvard T.H. Chan School of Public Health and Co-Editor in Chief of the Harvard Data Science Review. She is an elected member of the National Academy of Medicine and of the International Society of Mathematical Statistics. She leads an interdisciplinary group of scientists to address important questions in environmental health science, climate change, and health policy. Her contributions to the field have been remarkable including more than 250 peer-reviewed published articles, and has provided her knowledge on the topics on joint panels with New Jersey Senator Cory Booker, and European Commission). Dr. Dominici has provided the scientific community and policy makers with comprehensive and compelling evidence on the adverse health effects of air pollution, noise pollution, and climate change. Her studies have directly and routinely impacted air quality policy. Dr. Dominici was recognized in Thomson Reuter’s 2019 list of the most highly cited researchers–ranking in the top 1% of cited scientists in her field. Her work has been covered by the New York Times, the Los Angeles Times, BBC, the Guardian, CNN, and NPR. In April 2020 she has been awarded the Karl E. Peace Award for Outstanding Statistical Contributions for the Betterment of Society by the American Statistical Association. She is an advocate for the career advancement of women faculty, and her work on the Johns Hopkins University Committee on the Status of Women earned her the campus Diversity Recognition Award in 2009. At the Harvard T.H. Chan School of Public Health, she has led the Committee for the Advancement of Women Faculty.

Roberto Capobianco

Senior Research Scientist at Sony AI and a Contract Professor (previously Assistant Professor) at Sapienza University of Rome, Italy

Outracing champion Gran Turismo drivers with deep reinforcement learning

Many potential applications of artificial intelligence involve making real-time decisions in physical systems while interacting with humans. Automobile racing represents an extreme example of these conditions; drivers must execute complex tactical manoeuvres to pass or block opponents while operating their vehicles at their traction limits. Racing simulations, such as the PlayStation game Gran Turismo, faithfully reproduce the non-linear control challenges of real race cars while also encapsulating the complex multi-agent interactions. In this talk, I will describe how at Sony AI we trained agents for Gran Turismo that can compete with the world’s best e-sports drivers. Our work, that was featured on the cover of Nature, combines state-of the-art, model-free, deep reinforcement learning algorithms with mixed-scenario training to learn an integrated control policy that combines exceptional speed with impressive tactics. In addition, we construct a reward function that enables the agent to be competitive while adhering to racing’s important, but under-specified, sportsmanship rules. We demonstrate the capabilities of our agent, Gran Turismo Sophy, by winning a head-to-head competition against four of the world’s best Gran Turismo drivers. By describing how we trained championship-level racers, we demonstrate the possibilities and challenges of using these techniques to control complex dynamical systems in domains where agents must respect imprecisely defined human norms.

Biography

Roberto Capobianco is a Senior Research Scientist at Sony AI and a Contract Professor (previously Assistant Professor) at Sapienza University of Rome, where he founded the Knowledge, Reasoning and Learning Research Group, which he coordinates within the Cognitive Cooperating Robots Laboratory. Previously, he was a Research Scientist at Cogitai, Inc., as well as Head of AI at RADiCAL Solutions, LLC. With both academic and industrial experience in Reinforcement Learning (RL), Roberto’s main research interests lie at the edge between RL, robotics and explainability in Artificial Intelligence. He obtained his PhD from Sapienza University of Rome working on the generation and learning of semantic driven robot behaviors, and he has been a Research Scholar at the Robotics Institute of the Carnegie Mellon University (Pittsburgh, USA) working with Prof. Drew Bagnell. Roberto has been awarded a 3-year fellowship and a Research Starting Grant from Sapienza University of Rome, as well as the AAAI Robotics Fellowship in 2016.