Random Action Replay for Reinforcement Learning

An artificial intelligence (AI) platform to support random action replay for natural language (NL) learning. A NL conversation is explored to train a neural network. One or more tuples are leverage for the training, with each tuple representing an input action, a vector, an output action, and a rewa...

Full description

Saved in:
Bibliographic Details
Main Authors Yu, Yang, Zhang, Wei, Campbell, Murray Scott, Kumaravel, Sadhana
Format Patent
LanguageEnglish
Published 30.12.2021
Subjects
CALCULATING
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
COMPUTING
COUNTING
ELECTRIC DIGITAL DATA PROCESSING
HANDLING RECORD CARRIERS
PHYSICS
PRESENTATION OF DATA
RECOGNITION OF DATA
RECORD CARRIERS
Online AccessGet full text

Cover

More Information
Summary:An artificial intelligence (AI) platform to support random action replay for natural language (NL) learning. A NL conversation is explored to train a neural network. One or more tuples are leverage for the training, with each tuple representing an input action, a vector, an output action, and a reward value. An action is sampled from the vector, with the sampling including assessment of a corresponding first gradient. The first gradient is applied to selectively adjust the neural network. As NL input is received and applied to the selectively adjusted neural network, an output corresponding to the NL input is identified and a corresponding action is executed.
Bibliography:Application Number: US202016946586