Invention Grant
- Patent Title: Methods and systems for support policy learning
-
Application No.: US16875741Application Date: 2020-05-15
-
Publication No.: US11605026B2Publication Date: 2023-03-14
- Inventor: Daniel Mark Graves , Jun Jin , Jun Luo
- Applicant: Daniel Mark Graves , Jun Jin , Jun Luo
- Applicant Address: CA Edmonton; CA Edmonton; CA Toronto
- Assignee: Daniel Mark Graves,Jun Jin,Jun Luo
- Current Assignee: Daniel Mark Graves,Jun Jin,Jun Luo
- Current Assignee Address: CA Edmonton; CA Edmonton; CA Toronto
- Main IPC: G06N20/00
- IPC: G06N20/00

Abstract:
Methods and systems are described for support policy learning in an agent of a robot. A general value function (GVF) is learned for a main policy, where the GVF represents future performance of the agent executing the main policy for a given state of the environment. A master policy selects an action based on the predicted accumulated success value received from the general value function. When the predicted accumulated success value is an acceptable value, the action selected by the master policy is execution of the main policy. When the predicted accumulated success value is not an acceptable value, the master action causes a support policy to be learned. The support policy generates a support action to be performed which causes the robot to transition from to a new state where the predicted accumulated success value has an acceptable value.
Public/Granted literature
- US20210357782A1 METHODS AND SYSTEMS FOR SUPPORT POLICY LEARNING Public/Granted day:2021-11-18
Information query