Systems and Methods for Providing Reinforcement Learning in a Deep Learning System

Abstract

Systems and methods for providing reinforcement learning for a deep learning network are disclosed. A reinforcement learning process that provides deep exploration is provided by a bootstrap that applied to a sample of observed and artificial data to facilitate deep exploration via a Thompson sampling approach.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS[0001]The current application is a Continuation-In-Part Application of U.S. patent application Ser. No. 15 / 201,284 filed Jul. 1, 2016 that in turn claims priority to U.S. Provisional Application No. 62 / 187,681, filed Jul. 1, 2015, the disclosures of which are incorporated herein by reference as if set forth herewith.FIELD OF THE INVENTION[0002]This invention relates to deep learning networks including, but not limited to, artificial neural networks. More particularly, this invention relates to systems and methods for training deep learning networks from a set of training data using reinforcement learning.BACKGROUND OF THE INVENTION[0003]Deep learning networks including, but not limited to, artificial neural networks are machine learning systems that receive data, extract statistics and classify results. These systems use a training set of data to generate a model in order to make data driven decisions to provide a desired output.[0004]Deep lear...

AI Technical Summary

Benefits of technology

This patent describes systems and methods for using reinforcement learning in deep learning networks. This involves maintaining a deep neural network and applying a reinforcement learning process to it. The process involves receiving observed data and artificial data and generating training data based on a set of rules. The system then selects an action based on the training data, receives the result data, and updates the observed data with the result data. The process can also use a training mask to determine which data to use for training. Overall, this approach allows for improved learning and optimization in deep learning networks.

Problems solved by technology

These approaches are not practical in complex environments that require the system to generalize in order to operate properly.

Thus, these reinforcement learning approaches in large-scale application have relied upon either statistically inefficient exploration strategies or include no exploration at all.

Images