In multi-goal reinforcement learning for a given environment, agents learn policies to achieve multiple goals by using experiences gained from interactions with the environment. One of the key challenges in this setting is training agents using sparse binary rewards, which can be difficult due to a lack of successful experiences. To address this challenge, hindsight experience replay (HER) generates successful experiences from unsuccessful experiences. However, the process of generating successful experiences from uniformly sampled ones can be inefficient. In this paper, a novel approach called Failed goal Aware HER (FAHER) is proposed to enhance the sampling efficiency. The approach exploits the property of achieved goals in relation to failed goals that are defined as the original goals not achieved. The proposed method involves clustering episodes with different achieved goals using a cluster model and subsequently sampling experiences in the manner of HER. The cluster model is generated by applying a clustering algorithm to failed goals. The proposed method is validated by experiments with three robotic control tasks of the OpenAI gym. The results of experiments demonstrate that the proposed method is more sample efficient and achieves improved performance over baseline approaches.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Failed Goal Aware Hindsight Experience Replay


    Weitere Titelangaben:

    Lect. Notes in Networks, Syst.


    Beteiligte:
    Abdul Majeed, Anwar P.P. (Herausgeber:in) / Yap, Eng Hwa (Herausgeber:in) / Liu, Pengcheng (Herausgeber:in) / Huang, Xiaowei (Herausgeber:in) / Nguyen, Anh (Herausgeber:in) / Chen, Wei (Herausgeber:in) / Kim, Ue-Hwan (Herausgeber:in) / Kim, Taeyoung (Autor:in) / Jeong, Haechan (Autor:in) / Har, Dongsoo (Autor:in)

    Kongress:

    International Conference on Robot Intelligence Technology and Applications ; 2023 ; Taicang December 06, 2023 - December 08, 2023



    Erscheinungsdatum :

    29.11.2024


    Format / Umfang :

    12 pages





    Medientyp :

    Aufsatz/Kapitel (Buch)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch




    Intelligent Online Multiconstrained Reentry Guidance Based on Hindsight Experience Replay

    Qingji Jiang / Xiaogang Wang / Yuliang Bai et al. | DOAJ | 2023

    Freier Zugriff


    Explanation-Aware Experience Replay in Rule-Dense Environments

    Sovrano, Francesco / Raymond, Alex / Prorok, Amanda | BASE | 2022

    Freier Zugriff

    Trip Replay Experience

    GAYNOR PHILLIP KING | Europäisches Patentamt | 2018

    Freier Zugriff

    Trip replay experience

    GAYNOR PHILLIP KING | Europäisches Patentamt | 2018

    Freier Zugriff