51 citations · 93 across the 4 of their papers we have counts for
6 papers
Correcting Momentum in Temporal Difference Learning
Emmanuel Bengio, Joelle Pineau, Doina Precup
A common optimization tool used in deep reinforcement learning is momentum, which consists in accumulating and discounting past gradients, reapplying them at each iteration. We arg…
TDprop: Does Jacobi Preconditioning Help Temporal Difference Learning?
Joshua Romoff, Peter Henderson, David Kanaa +4
We investigate whether Jacobi preconditioning, accounting for the bootstrap term in temporal difference (TD) learning, can help boost performance of adaptive optimizers. Our method…
Interference and Generalization in Temporal Difference Learning
Emmanuel Bengio, Joelle Pineau, Doina Precup
We study the link between generalization and interference in temporal-difference (TD) learning. Interference is defined as the inner product of two different gradients, representin…
Disentangling the independently controllable factors of variation by interacting with the world
Valentin Thomas, Emmanuel Bengio, William Fedus +6
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of traini…
Independently Controllable Factors
Valentin Thomas, Jules Pondard, Emmanuel Bengio +6
It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of traini…
Independently Controllable Features
Emmanuel Bengio, Valentin Thomas, Joelle Pineau +2
Finding features that disentangle the different causes of variation in real data is a difficult task, that has nonetheless received considerable attention in static domains like na…