Tag Archives: learning

Dynamic Programming in Distributional Reinforcement Learning

Last summer, I supervised a summer intern, Cédric Odin, student at Ecole Normale in Ker Lann, France, on Dynamic Programming in Distributional Reinforcement Learning. A state-of-the-art is now available online https://hal.archives-ouvertes.fr/hal-03168889

The classic approach to reinforcement learning is limited in that it only predicts the expected return. The specialized literature has long tried to remedy this problem by studying risk-sensitive models, but the distributional approach will not emerge until 2017. Since the seminal article Bellemare, Dabney, and Munos 2017 and the state-of-the-art performance of the C51 algorithm in the ATARI 2600 suite of benchmark tasks (Bellemare, Naddaf, et al. 2013), research has focused on understanding the behaviour of distributional algorithms. In this paper we place Bellemare’s original results in distributional dynamic programming in parallel with the classic results.

Econometrics and Machine Learning

I will be in London, UK, at the Centre for Central Banking Studies, invited as a keynote speaker for a major conference. For my talk, on Econometric Models and Statistical Learning Techniques, the agenda is the follownig

  • introduction on High Dimensional Data and Modeling
  • foundations of econometric models, and probabilistic aspects
  • machine learning techniques, with a discussion on boosting, cross validation
  • classification, from the logistic regression to trees and random forest
  • machine learning tools that can be used in econometrics, such as bootstrap, principal component analysis / partial least squares, and instrumental variables and variable selection

Slides are avaible (as usual, the pdf version is more informative than the one on slideshare where animations are missing)