Timezone: »

A Consciousness-Inspired Planning Agent for Model-Based Reinforcement Learning
Mingde Zhao · Zhen Liu · Sitao Luan · Shuyuan Zhang · Doina Precup · Yoshua Bengio
Event URL: https://openreview.net/forum?id=B6On_2LEkTh »

We present an end-to-end, model-based deep reinforcement learning agent which dynamically attends to relevant parts of its state, in order to plan and to generalize better out-of-distribution. The agent's architecture uses a set representation and a bottleneck mechanism, forcing the number of entities to which the agent attends at each planning step to be small. In experiments, we investigate the bottleneck mechanism with sets of customized environments featuring different dynamics. We consistently observe that the design allows agents to learn to plan effectively, by attending to the relevant objects, leading to better out-of-distribution generalization.

Author Information

Mingde Zhao (McGill University)
Zhen Liu (University of Montreal, MILA)
Sitao Luan (McGill University, Mila)

I’m a second year Ph.D. student working with Professor Doina Precup and Professor Xiao-Wen Chang on the cross area of reinforcement learning and matrix computations. I’m currently interested in approximate dynamic programming and Krylov subspace methods. I'm currently working on constructiong basis functions for value function approximation in model-based reinforcement learning.

Shuyuan Zhang (Mcgill University / Mila)
Doina Precup (DeepMind)
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.

More from the Same Authors