A machine learning model for reinforcement learning uses parameterized families of Markov decision processes (MDP) with latent variables. The system uses latent variables to improve ability of models to transfer knowledge and generalize to new tasks. Accordingly, trained machine learning based models are able to work in unseen environments or combinations of conditions/factors that the machine learning model was never trained on. For example, robots or self-driving vehicles based on the machine learning based models are robust to changing goals and are able to adapt to novel reward functions or tasks flexibly while being able to transfer knowledge about environments and agents to new tasks.
MODEL BASED REINFORCEMENT LEARNING BASED ON GENERALIZED HIDDEN PARAMETER MARKOV DECISION PROCESSES
2020-11-26
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 |
Multiscale Uncertainty Quantification Based on a Generalized Hidden Markov Model
Online Contents | 2011
|Learning Profiles Based on Hierarchical Hidden Markov Model
British Library Conference Proceedings | 2005
|Hidden Markov Model-based population synthesis
Elsevier | 2016
|Hidden Markov Model-based population synthesis
Online Contents | 2016
|HIDDEN MARKOV MODEL PARAMETER ESTIMATION FOR MULTIPLE DIM TARGET DETECTION
British Library Conference Proceedings | 2012
|