Kenneth Edward Stanley
Accountancy in Austin, TX
License number
Colorado 6090
Issued Date
Jan 29, 1981
Renew Date
May 31, 1996
Expiration Date
May 31, 1996
Type
Certified Public Accountant
Address
Address
Austin National Bank Tower #1750, Austin, TX 78701
Professional information
Method And Apparatus For Providing Real-Time Machine Learning To Computer-Controlled Agents Used In Video Games
US Patent:
7559843, Jul 14, 2009
Filed:
Aug 4, 2005
Appl. No.:
11/197065
Inventors:
Kenneth O. Stanley - Austin TX, US
Risto Miikkulainen - Austin TX, US
Risto Miikkulainen - Austin TX, US
Assignee:
Board of Regents, The University of Texas System - Austin TX
International Classification:
A63F 9/24, A63F 13/00, G06F 17/00, G06F 19/00, G06N 3/02
US Classification:
463 42, 463 43, 463 21, 463 23, 706 15
Abstract:
A method for providing real-time machine learning to agents used in video games is disclosed. Initially, adjusted fitnesses of a set of agents within a population are determined. An agent having a relatively low adjusted fitness is then removed from the population. Subsequently, a parent agent is probabilistically selected from the population to generate an offspring agent. Finally, the removed agent is replaced by the offspring agent, maintaining a continuous real-time replacement cycle.
Deriving A Genome Representation For Evolving Graph Structure Weights
US Patent:
6988089, Jan 17, 2006
Filed:
May 2, 2001
Appl. No.:
09/847869
Inventors:
Evan Randy Kirshenbaum - Mountain View CA, US
Kenneth O. Stanley - Austin TX, US
Bin Zhang - Fremont CA, US
Kenneth O. Stanley - Austin TX, US
Bin Zhang - Fremont CA, US
Assignee:
Hewlett-Packard Development Company, L.P. - Houston TX
International Classification:
G06F 15/18
US Classification:
706 14, 706 13
Abstract:
A method for deriving a genome representation for the weights in a graph structure that increases the likelihood that solutions to substructures of the graph structure will be preserved during crossover operations. The preservation of solutions to substructures across generations of organisms may decrease the computational time when evolving to a desired solution.