A framework for offline learning from a set of diverse and suboptimal demonstrations operates by selectively imitating local sequences from the dataset. At least one embodiment recovers performant policies from large manipulation datasets by decomposing the problem into a goal-conditioned imitation and a high-level goal selection mechanism.


    Access

    Download


    Export, share and cite



    Title :

    MACHINE LEARNING USING MODULAR SOLUTION DATASETS


    Contributors:

    Publication date :

    2022-02-24


    Type of media :

    Patent


    Type of material :

    Electronic Resource


    Language :

    English


    Classification :

    IPC:    B62D MOTOR VEHICLES , Motorfahrzeuge / 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 / G06N COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS , Rechnersysteme, basierend auf spezifischen Rechenmodellen



    A Fundamental Study on Suicides and Rainfall Datasets Using basic Machine Learning Algorithms

    Harita, U. / Kumar, V. Uday / Sudarsa, Dorababu et al. | IEEE | 2020


    Physics Infused Machine Learning Based Prediction of VTOL Aerodynamics with Sparse Datasets

    Oddiraju, Manaswin / Amin, Divyang / Piedmonte, Michael et al. | TIBKAT | 2023


    Physics Infused Machine Learning Based Prediction of VTOL Aerodynamics with Sparse Datasets

    Oddiraju, Manaswin / Amin, Divyang / Piedmonte, Michael et al. | AIAA | 2023


    Feature Extraction and Classification from Planetary Science Datasets enabled by Machine Learning

    Nixon, Conor A. / Yahn, Zachary / Duncan, Ethan et al. | IEEE | 2023


    Effects of Different Training Datasets on Machine Learning Models for Pavement Performance Prediction

    Aranha, Ana Luisa / Bernucci, Liedi Légi Bariani / Vasconcelos, Kamilla L. | Transportation Research Record | 2023