Patents by Inventor Matthew Kretchmar

Matthew Kretchmar has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Control system and technique employing reinforcement learning having stability and learning phases
    Patent number: 6665651
    Abstract: A feedback control system for automatic on-line training of a controller for a plant, the system having a reinforcement learning agent connected in parallel with the controller. The learning agent comprises an actor network and a critic network operatively arranged to carry out at least one sequence of a stability phase followed by a learning phase. During the stability phase, a multi-dimensional boundary of values is determined. During the learning phase, a plurality of updated weight values is generated in connection with the on-line training, if and until one of the updated weight values reaches the boundary, at which time a next sequence is carried out to determine a next multi-dimensional boundary of values followed by a next learning phase.
    Type: Grant
    Filed: July 18, 2002
    Date of Patent: December 16, 2003
    Assignee: Colorado State University Research Foundation
    Inventors: Peter M. Young, Charles Anderson, Douglas C. Hittle, Matthew Kretchmar
  • Control system and technique employing reinforcement learning having stability and learning phases
    Publication number: 20030074338
    Abstract: A feedback control system for automatic on-line training of a controller for a plant, the system having a reinforcement learning agent connected in parallel with the controller. The learning agent comprises an actor network and a critic network operatively arranged to carry out at least one sequence of a stability phase followed by a learning phase. During the stability phase, a multi-dimensional boundary of values is determined. During the learning phase, a plurality of updated weight values is generated in connection with the on-line training, if and until one of the updated weight values reaches the boundary, at which time a next sequence is carried out to determine a next multi-dimensional boundary of values followed by a next learning phase.
    Type: Application
    Filed: July 18, 2002
    Publication date: April 17, 2003
    Inventors: Peter M. Young, Charles Anderson, Douglas C. Hittle, Matthew Kretchmar