Skip to yearly menu bar Skip to main content


Poster

Highway Value Iteration Networks

Yuhui Wang · Weida Li · Francesco Faccio · Qingyuan Wu · Jürgen Schmidhuber

Hall C 4-9 #1401
[ ] [ Paper PDF ]
[ Slides
Wed 24 Jul 4:30 a.m. PDT — 6 a.m. PDT

Abstract:

Value iteration networks (VINs) enable end-to-end learning for planning tasks by employing a differentiable "planning module" that approximates the value iteration algorithm. However, long-term planning remains a challenge because training very deep VINs is difficult. To address this problem, we embed highway value iteration---a recent algorithm designed to facilitate long-term credit assignment---into the structure of VINs. This improvement augments the "planning module" of the VIN with three additional components: 1) an "aggregate gate," which constructs skip connections to improve information flow across many layers; 2) an "exploration module," crafted to increase the diversity of information and gradient flow in spatial dimensions; 3) a "filter gate" designed to ensure safe exploration. The resulting novel highway VIN can be trained effectively with hundreds of layers using standard backpropagation. In long-term planning tasks requiring hundreds of planning steps, deep highway VINs outperform both traditional VINs and several advanced, very deep NNs.

Chat is not available.