Some content of this application is unavailable at the moment.
If this situation persist, please contact us atFeedback&Contact
1. (US20150100530) Methods and apparatus for reinforcement learning

Application Number: 14097862 Application Date: 05.12.2013
Publication Number: 20150100530 Publication Date: 09.04.2015
Grant Number: 09679258 Grant Date: 13.06.2017
Publication Kind : B2
IPC:
G06N 99/00
G06N 3/04
G06N 3/00
A63F 13/67
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
99
Subject matter not provided for in other groups of this subclass
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
02
using neural network models
04
Architecture, e.g. interconnection topology
G PHYSICS
06
COMPUTING; CALCULATING; COUNTING
N
COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3
Computer systems based on biological models
[IPC code unknown for A63F 13/67]
Applicants:
Inventors:
Priority Data:
Title: (EN) Methods and apparatus for reinforcement learning
Abstract: front page image
(EN)

We describe a method of reinforcement learning for a subject system having multiple states and actions to move from one state to the next. Training data is generated by operating on the system with a succession of actions and used to train a second neural network. Target values for training the second neural network are derived from a first neural network which is generated by copying weights of the second neural network at intervals.