papers AI Learner
The Github is limit! Click to go to the new site.

Value Propagation Networks

2019-03-25
Nantas Nardelli, Gabriel Synnaeve, Zeming Lin, Pushmeet Kohli, Philip H. S. Torr, Nicolas Usunier

Abstract

We present Value Propagation (VProp), a set of parameter-efficient differentiable planning modules built on Value Iteration which can successfully be trained using reinforcement learning to solve unseen tasks, has the capability to generalize to larger map sizes, and can learn to navigate in dynamic environments. We show that the modules enable learning to plan when the environment also includes stochastic elements, providing a cost-efficient learning system to build low-level size-invariant planners for a variety of interactive navigation problems. We evaluate on static and dynamic configurations of MazeBase grid-worlds, with randomly generated environments of several different sizes, and on a StarCraft navigation scenario, with more complex dynamics, and pixels as input.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1805.11199

PDF

http://arxiv.org/pdf/1805.11199


Similar Posts

Comments