Timezone: »

Systematic Evaluation of Causal Discovery in Visual Model Based Reinforcement Learning
Nan Rosemary Ke · Aniket Didolkar · Sarthak Mittal · Anirudh Goyal ALIAS PARTH GOYAL · Guillaume Lajoie · Stefan Bauer · Danilo Jimenez Rezende · Michael Mozer · Yoshua Bengio · Chris Pal

Inducing causal relationships from observations is a classic problem in machine learning. Most work in causality starts from the premise that the causal variables themselves are observed. However, for AI agents such as robots trying to make sense of their environment, the only observables are low-level variables like pixels in images. To generalize well, an agent must induce high-level variables, particularly those which are causal or are affected by causal variables. A central goal for AI and causality is thus the joint discovery of abstract representations and causal structure. However, we note that existing environments for studying causal induction are poorly suited for this objective because they have complicated task-specific causal graphs which are impossible to manipulate parametrically (e.g., number of nodes, sparsity, causal chain length, etc.). In this work, our goal is to facilitate research in learning representations of high-level variables as well as causal structures among them. In order to systematically probe the ability of methods to identify these variables and structures, we design a suite of benchmarking RL environments. We evaluate various representation learning algorithms from the literature and find that explicitly incorporating structure and modularity in models can help causal induction in model-based reinforcement learning.

Author Information

Nan Rosemary Ke (DeepMind)
Aniket Didolkar (University of Montreal)
Sarthak Mittal (Universite de Montreal / MILA)
Anirudh Goyal ALIAS PARTH GOYAL (Université de Montréal)
Guillaume Lajoie (Mila, Université de Montréal)
Stefan Bauer (Max Planck institute)
Danilo Jimenez Rezende (Google DeepMind)
Michael Mozer (Google Research / University of Colorado)
Yoshua Bengio (Mila / U. Montreal)

Yoshua Bengio (PhD'1991 in Computer Science, McGill University). After two post-doctoral years, one at MIT with Michael Jordan and one at AT&T Bell Laboratories with Yann LeCun, he became professor at the department of computer science and operations research at Université de Montréal. Author of two books (a third is in preparation) and more than 200 publications, he is among the most cited Canadian computer scientists and is or has been associate editor of the top journals in machine learning and neural networks. Since '2000 he holds a Canada Research Chair in Statistical Learning Algorithms, since '2006 an NSERC Chair, since '2005 his is a Senior Fellow of the Canadian Institute for Advanced Research and since 2014 he co-directs its program focused on deep learning. He is on the board of the NIPS foundation and has been program chair and general chair for NIPS. He has co-organized the Learning Workshop for 14 years and co-created the International Conference on Learning Representations. His interests are centered around a quest for AI through machine learning, and include fundamental questions on deep learning, representation learning, the geometry of generalization in high-dimensional spaces, manifold learning and biologically inspired learning algorithms.

Chris Pal (Montreal Institute for Learning Algorithms, École Polytechnique, Université de Montréal)

More from the Same Authors