Computer-implemented methods, systems, and apparatus, including computer-readable medium, for generating an action selection policy for causing an execution device to complete a task are described. Data representing a task that is divided into a sequence of subtasks are obtained. For a specified subtask except for a first subtask in the sequence of subtasks, a value neural network (VNN) is trained. The VNN receives inputs include reach probabilities of reaching a subtask initial state of the specified subtask, and predicts a reward of the execution device in the subtask initial state of the specified subtask. A strategy neural network (SNN) for a prior subtask that precedes the specified subtask is trained based on the VNN. The SNN receives inputs include a sequence of actions that reach a subtask state of the prior subtask, and predicts an action selection policy of the execution device in the subtask state of the prior subtask.
Determining action selection policies of an execution device
2021-10-26
Patent
Electronic Resource
English
IPC: | G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen / B60W CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION , Gemeinsame Steuerung oder Regelung von Fahrzeug-Unteraggregaten verschiedenen Typs oder verschiedener Funktion / G06K Erkennen von Daten , RECOGNITION OF DATA / G06F ELECTRIC DIGITAL DATA PROCESSING , Elektrische digitale Datenverarbeitung |
DETERMINING ACTION SELECTION POLICIES OF AN EXECUTION DEVICE
European Patent Office | 2021
|ACTION SELECTION DEVICE, ACTION SELECTION PROGRAM, AND ACTION SELECTION METHOD
European Patent Office | 2019
|