Invention Application
- Patent Title: HIERARCHICAL POLICIES FOR MULTITASK TRANSFER
-
Application No.: US17613687Application Date: 2020-05-22
-
Publication No.: US20220237488A1Publication Date: 2022-07-28
- Inventor: Markus Wulfmeier , Abbas Abdolmaleki , Roland Hafner , Jost Tobias Springenberg , Nicolas Manfred Otto Heess , Martin Riedmiller
- Applicant: DeepMind Technologies Limited
- Applicant Address: GB London
- Assignee: DeepMind Technologies Limited
- Current Assignee: DeepMind Technologies Limited
- Current Assignee Address: GB London
- International Application: PCT/EP2020/064336 WO 20200522
- Main IPC: G06N7/00
- IPC: G06N7/00 ; G06N3/04 ; G06N20/20

Abstract:
Methods, systems, and apparatus, including computer programs encoded on computer storage media, for controlling an agent. One of the methods includes obtaining an observation characterizing a current state of the environment and data identifying a task currently being performed by the agent; processing the observation and the data identifying the task using a high-level controller to generate a high-level probability distribution that assigns a respective probability to each of a plurality of low-level controllers; processing the observation using each of the plurality of low-level controllers to generate, for each of the plurality of low-level controllers, a respective low-level probability distribution; generating a combined probability distribution; and selecting, using the combined probability distribution, an action from the space of possible actions to be performed by the agent in response to the observation.
Information query
IPC分类:
G | 物理 |
G06 | 计算;推算或计数 |
G06N | 基于特定计算模型的计算机系统 |
G06N7/00 | 基于特定数学模式的计算机系统 |