Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
In reinforcement learning, all objective functions are not equal
Romain Laroche \& Harm van Seijen
Feb 12, 2018 (modified: Feb 13, 2018)ICLR 2018 Workshop Submissionreaders: everyone
Abstract:We study the learnability of Q-functions. We get the reward back propagation out of the way by fitting directly the Q-network on the analytically computed Q^*, given a chosen objective function. We show that some objective functions are easier to train than others by several magnitude orders. We observe in particular the influence of the gamma parameter and the decomposition of the task into subtasks.
TL;DR:In reinforcement learning, all objective functions are not equal
Keywords:reinforcement learning, deep learning
Enter your feedback below and we'll get back to you as soon as possible.