Processing

Please wait...

Settings

Settings

Goto Application

1. WO2020112186 - AUTONOMOUS SYSTEM INCLUDING A CONTINUALLY LEARNING WORLD MODEL AND RELATED METHODS

Publication Number WO/2020/112186
Publication Date 04.06.2020
International Application No. PCT/US2019/047758
International Filing Date 22.08.2019
IPC
G06N 3/08 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
08Learning methods
G06N 3/04 2006.01
GPHYSICS
06COMPUTING; CALCULATING OR COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architecture, e.g. interconnection topology
CPC
G06F 17/15
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
FELECTRIC DIGITAL DATA PROCESSING
17Digital computing or data processing equipment or methods, specially adapted for specific functions
10Complex mathematical operations
15Correlation function computation ; including computation of convolution operations
G06N 3/006
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
004Artificial life, i.e. computers simulating life
006based on simulated virtual individual or collective life forms, e.g. single "avatar", social simulations, virtual worlds or particle swarm optimisation
G06N 3/0445
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0445Feedback networks, e.g. hopfield nets, associative networks
G06N 3/0454
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0454using a combination of multiple neural nets
G06N 3/0472
GPHYSICS
06COMPUTING; CALCULATING; COUNTING
NCOMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
3Computer systems based on biological models
02using neural network models
04Architectures, e.g. interconnection topology
0472using probabilistic elements, e.g. p-rams, stochastic processors
Applicants
  • HRL LABORATORIES, LLC [US]/[US]
Inventors
  • KETZ, Nicholas, A.
  • PILLY, Praveen, K.
  • KOLOURI, Soheil
  • MARTIN, Charles, E.
  • HOWARD, Michael, D.
Agents
  • SZAKALSKI, Dustin, R.
Priority Data
62/749,81924.10.2018US
Publication Language English (EN)
Filing Language English (EN)
Designated States
Title
(EN) AUTONOMOUS SYSTEM INCLUDING A CONTINUALLY LEARNING WORLD MODEL AND RELATED METHODS
(FR) SYSTÈME AUTONOME COMPRENANT UN MODÈLE DU MONDE À APPRENTISSAGE CONTINU ET PROCÉDÉS ASSOCIÉS
Abstract
(EN)
An autonomous or semi-autonomous system includes a temporal prediction network configured to process a first set of samples from an environment of the system during performance of a first task, a controller configured to process the first set of samples from the environment and a hidden state output by the temporal prediction network, a preserved copy of the temporal prediction network, and a preserved copy of the controller. The preserved copy of the temporal prediction network and the preserved copy of the controller are configured to generate simulated rollouts, and the system is configured to interleave the simulated rollouts with a second set of samples from the environment during performance of a second task to preserve knowledge of the temporal prediction network for performing the first task.
(FR)
La présente invention concerne un système autonome ou semi-autonome qui comprend un réseau de prédiction temporelle configuré pour traiter un premier ensemble d'échantillons d'un environnement du système pendant la réalisation d'une première tâche, un contrôleur configuré pour traiter le premier ensemble d'échantillons de l'environnement et un état caché délivré par le réseau de prédiction temporelle, une copie préservée du réseau de prédiction temporelle et une copie préservée du contrôleur. La copie préservée du réseau de prédiction temporelle et la copie préservée du contrôleur sont configurées pour générer des transferts simulés, et le système est configuré pour entrelacer les transferts simulés avec un second ensemble d'échantillons de l'environnement pendant la réalisation d'une seconde tâche pour préserver la connaissance du réseau de prédiction temporelle permettant de réaliser la première tâche.
Latest bibliographic data on file with the International Bureau