In recent years, reinforcement learning (RL) has been widely used in decision-making. However, it still faces challenges when it is applied to autonomous driving, especially in complex multi-task scenarios. This paper introduces an unsupervised reinforcement learning(URL), called an improved Contrastive Intrinsic Control (CIC), to address this problem. CIC generates skills as transferable factors between different tasks to enable multi-task expansion. By comparing skills as potential state transfers with real state transfers, the mutual information between the two serves as the curiosity that drives the agents to explore the environment and gather experience in advance. This helps the collection of valuable experiences and the acquisition of effective skills. In the multi-task expansion phase, the unified training skills are used as a prior to enabling rapid convergence in various environments. Unified training is performed without rewards, followed by repeated training on multiple downstream tasks. Experiments are conducted in a highway environment, where three different driving modes are differentiated as separate RL tasks through reward functions. The experimental results demonstrate that the proposed method possesses the ability of multi-task learning. Compared to the Deep Deterministic Policy Gradient (DDPG) baseline, it achieves a 30% to 50% improvement in convergence speed at the single-task level and a 20% to 40% improvement in the final learning performance. Furthermore, even in complex tasks, where other RL methods struggle to learn effectively, it still achieves an obvious learning ability. This approach realizes an effective combination of curiosity mechanism, and RL decision making in the multitasking domain.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Unsupervised Reinforcement Learning for Multi-Task Autonomous Driving: Expanding Skills and Cultivating Curiosity


    Beteiligte:
    Ma, Zhenyu (Autor:in) / Liu, Xinyi (Autor:in) / Huang, Yanjun (Autor:in)

    Erschienen in:

    Erscheinungsdatum :

    01.10.2024


    Format / Umfang :

    3600805 byte




    Medientyp :

    Aufsatz (Zeitschrift)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Efficient Reinforcement Learning for Autonomous Driving with Parameterized Skills and Priors

    Wang, Letian / Liu, Jie / Shao, Hao et al. | ArXiv | 2023

    Freier Zugriff


    Curiosity-Driven Attention for Anomaly Road Obstacles Segmentation in Autonomous Driving

    Ren, Xiangxuan / Li, Min / Li, Zhenhua et al. | IEEE | 2023


    Autonomous Driving with Deep Reinforcement Learning

    Zhu, Yuhua / Technische Universität Dresden | SLUB | 2023


    LEARNING UNSUPERVISED WORLD MODELS FOR AUTONOMOUS DRIVING VIA DISCRETE DIFFUSION

    ZHANG LUNJUN / XIONG YUWEN / YANG ZE et al. | Europäisches Patentamt | 2025

    Freier Zugriff