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

Deep Recurrent Q-Learning vs Deep Q-Learning on a simple Partially Observable Markov Decision Process with Minecraft

2019-04-11
Clément Romac, Vincent Béraud

Abstract

Deep Q-Learning has been successfully applied to a wide variety of tasks in the past several years. However, the architecture of the vanilla Deep Q-Network is not suited to deal with partially observable environments such as 3D video games. For this, recurrent layers have been added to the Deep Q-Network in order to allow it to handle past dependencies. We here use Minecraft for its customization advantages and design two very simple missions that can be frames as Partially Observable Markov Decision Process. We compare on these missions the Deep Q-Network and the Deep Recurrent Q-Network in order to see if the latter, which is trickier and longer to train, is always the best architecture when the agent has to deal with partial observability.

Abstract (translated by Google)
URL

http://arxiv.org/abs/1903.04311

PDF

http://arxiv.org/pdf/1903.04311


Similar Posts

Comments