ML Meetup - Building Different Roads to Causal Structure & Deep Reinforcement Learning

Ricardo Silva and David Silver present their respective research on Causal Structure & Deep Reinforcement Learning.

At Man Group, we believe in the Python ecosystem and have been trading Machine Learning based systems since early 2014. To give back and strengthen London’s Python and Machine Learning Communities, we sponsor and support the PyData and Machine Learning London Meetups.

In January, we had the pleasure of welcoming Ricardo Silva, Associate Professor in Statistical Science at University College London, and David Silver, Principal research scientist at DeepMind and Professor at University College London to the London Machine Learning Meetup.

Building Different Roads to Causal Structure - Ricardo Silva

I will be presenting an overview of the role of causal assumptions for the prediction of the effects of an action, particularly when only observational data or limited interventions are available. This is a fundamental problem for any data driven investigation, from understanding the link between smoking and lung cancer to assessing the effectiveness of a marketing campaign. I will provide background and motivation to the problem, followed by a suite of different machine learning algorithms to disentangle causation from association under a variety of assumptions. This includes a view of the role of both combinatorial and differentiable optimization algorithms, and a continuum of trade-offs between the strength of our assumptions and the precision of our answers. Ultimately, this provides many roads to reduce our ignorance about one of the trickiest and most relevant questions in the empirical sciences: how does one thing cause another when many confounding factors that I do not fully control are still lurking in the background?

Ricardo Silva

Ricardo Silva obtained his PhD in 2005 from Carnegie Mellon University, at the recently founded Machine Learning Department. After a period as a postdoctoral researcher in the Gatsby Computational Neuroscience Unit, UCL, and the Statistical Laboratory, Cambridge, Ricardo joined the Statistical Science department at UCL, where currently he is an Associate Professor. Since 2016, Ricardo has also been appointed as a Faculty Fellow of the Alan Turing Institute. His research focuses on computational approaches and causal modelling for problems in a variety of areas, more recently on large-scale spatiotemporal analytics and fairness.

 

Deep Reinforcement Learning from AlphaGo to AlphaStar - David Silver

Recently, self-learning systems have achieved remarkable success in several challenging problems for artificial intelligence, by combining reinforcement learning with deep neural networks. In this talk, I describe the ideas and algorithms that led to AlphaGo: the first program to defeat a human champion in the game of Go; AlphaZero: which learned, from scratch, to also defeat the world computer champions in chess and shogi; and AlphaStar: the first program to defeat a human champion in the real-time strategy game of StarCraft.

David Silver

David Silver is a principal research scientist at DeepMind and a professor at University College London. David’s work focuses on artificially intelligent agents based on reinforcement learning. David co-led the project that combined deep learning and reinforcement learning to play Atari games directly from pixels (Nature 2015). He also led the AlphaGo project, culminating in the first program to defeat a top professional player in the full-size game of Go (Nature 2016), and the AlphaZero project, which learned by itself to defeat the world’s strongest chess, shogi and Go programs (Nature 2017, Science 2018). Most recently, he co-led the AlphaStar project, which led to the world’s first grandmaster level StarCraft player (Nature 2019). His work has been recognised by the Marvin Minsky award, Mensa Foundation Prize, and Royal Academy of Engineering Silver Medal.