The Policy Gradient approach is a subset of the Deep Reinforcement Learning (DRL) combines Deep Neural Networks (DNN) with Reinforcement Learning (RL). This approach finds the optimal policy of robot movement, based on the experience it gains from interaction with its environment. Unlike previous policy gradient algorithms, which were unable to handle the two types of error variance and bias introduced by the DNN model due to over- or underestimation, this algorithm is capable of handling both types of error variance and bias. This article will discuss the state-of-the-art SOTA policy gradient technique, trust region policy optimization (TRPO), by applying this method in various environments compared to another policy gradient method, the Proximal Policy Optimization (PPO), to explain their robust optimization, using this SOTA to gather experience data during various training phases after observing the impact of hyper-parameters on neural network performance.


    Access

    Download


    Export, share and cite



    Title :

    Robot Movement Using the Trust Region Policy Optimization



    Publication date :

    2023-01-01



    Type of media :

    Conference paper


    Type of material :

    Electronic Resource


    Language :

    English



    Classification :

    DDC:    629



    Progressive Validity Trust Region Optimization

    Thomson, Quinn / Martins, Joaquim R. R. A. | AIAA | 2008


    Progressive Validity Trust Region Optimization

    Thomson, Q. / Martins, J. / American Institute of Aeronautics and Astronautics | British Library Conference Proceedings | 2008


    Reliability Based Wing Design Optimization Using Trust Region Framework

    Kim, Suwhan / Ahn, Joongki / Kwon, Jang Hyuk | AIAA | 2004


    ROBOT MOVEMENT AND ONLINE TRAJECTORY OPTIMIZATION

    DEITS ROBIN / KUINDERSMA SCOTT / KELLY MATTHEW P et al. | European Patent Office | 2024

    Free access

    Robot movement and online trajectory optimization

    DEITS ROBIN / KUINDERSMA SCOTT / KELLY MATTHEW P et al. | European Patent Office | 2023

    Free access