Login| Sign Up| Help| Contact|

Patent Searching and Data


Title:
REINFORCEMENT LEARNING WITH INDUCTIVE LOGIC PROGRAMMING
Document Type and Number:
WIPO Patent Application WO/2023/083113
Kind Code:
A1
Abstract:
Methods and systems for training a model and automated motion include learning Markov decision processes using reinforcement learning in respective training environments. Logic rules are extracted from the Markov decision processes. T reward logic neural network (LNN) and a safety LNN are trained using the logic rules extracted from the Markov decision processes. The reward LNN and the safety LNN each take a state-action pair as an input and output a corresponding score for the state-action pair.

Inventors:
WACHI AKIFUMI (JP)
LU SONGTAO (US)
Application Number:
PCT/CN2022/129868
Publication Date:
May 19, 2023
Filing Date:
November 04, 2022
Export Citation:
Click for automatic bibliography generation   Help
Assignee:
IBM (US)
IBM CHINA CO LTD (CN)
International Classes:
G06N3/04; G05B13/04; G05D1/02; G06N20/00
Domestic Patent References:
WO2019071909A12019-04-18
Foreign References:
CN113060160A2021-07-02
CN113219968A2021-08-06
CN109948781A2019-06-28
CN113110359A2021-07-13
Attorney, Agent or Firm:
LIU, SHEN & ASSOCIATES (CN)
Download PDF:
View/Download PDF      PDF Help



 
Previous Patent: DETECTION METHOD, DETECTION APPARATUS, OPTICAL FIBER SYSTEM AND NETWORK DEVICE

Next Patent: DYNAMIC DATABASE OBJECT DESCRIPTION ADJUSTMENT