Title:
能動的探索なしの強化学習に基づく制御ポリシー学習及び車両制御方法
Document Type and Number:
Japanese Patent JP6856575
Kind Code:
B2
Abstract:
To provide a computer-implemented method for autonomously controlling a vehicle in order to perform a vehicle operation.SOLUTION: The method includes steps of: applying a passive actor-critic reinforcement learning method to passively collected data relating to the vehicle operation to learn a control policy configured for controlling the vehicle in order to perform the vehicle operation with a minimum expected cumulative cost; and controlling the vehicle in accordance with the control policy to perform the vehicle operation.SELECTED DRAWING: Figure 6
Inventors:
Tomoki Nishi
Application Number:
JP2018091189A
Publication Date:
April 07, 2021
Filing Date:
May 10, 2018
Export Citation:
Assignee:
Toyota Motor Engineering and Manufacturing North America, Inc.
International Classes:
B60W50/00; B60W30/00; B60W30/10; G06N99/00
Domestic Patent References:
| JP2004348394A |
Foreign References:
| US20180373245 | ||||
| US20190035275 | ||||
| WO2004068399A1 |
Attorney, Agent or Firm:
Atsushi Aoki
Shinji Mitsuhashi
Jun Tsuruta
Koichi Ito
Nobuo Sekine
Shinji Mitsuhashi
Jun Tsuruta
Koichi Ito
Nobuo Sekine