Reinforcement Learning (RL) has become an increasingly important research area as the success of machine learning algorithms and methods grows. To combat the safety concerns surrounding the freedom given to RL agents while training, there has been an increase in work concerning Safe Reinforcement Learning (SRL). However, these new and safe methods have been held to less scrutiny than their unsafe counterparts. For instance, comparisons among safe methods often lack fair evaluation across similar initial condition bounds and hyperparameter settings, use poor evaluation metrics, and cherry-pick the best training runs rather than averaging over multiple random seeds. In this work, we conduct an ablation study using evaluation best practices to investigate the impact of run time assurance (RTA), which monitors the system state and intervenes to assure safety, on effective learning. By studying multiple RTA approaches in both on-policy and off-policy RL algorithms, we seek to understand which RTA methods are most effective, whether the agents become dependent on the RTA, and the importance of reward shaping versus safe exploration in RL agent training. Our conclusions shed light on the most promising directions of SRL, and our evaluation methodology lays the groundwork for creating better comparisons in future SRL work.


    Zugriff

    Zugriff prüfen

    Verfügbarkeit in meiner Bibliothek prüfen

    Bestellung bei Subito €


    Exportieren, teilen und zitieren



    Titel :

    Ablation Study of How Run Time Assurance Impacts the Training and Performance of Reinforcement Learning Agents


    Beteiligte:


    Erscheinungsdatum :

    2023-07-01


    Format / Umfang :

    1476233 byte





    Medientyp :

    Aufsatz (Konferenz)


    Format :

    Elektronische Ressource


    Sprache :

    Englisch



    Runtime Safety Assurance Using Reinforcement Learning

    Lazarus, Christopher / Lopez, James G. / Kochenderfer, Mykel J. | IEEE | 2020


    UnityFlexML: Training Reinforcement Learning Agents in a Simulated Surgical Environment

    Eleonora Tagliabue / Ameya Pore / Diego Dall’Alba et al. | BASE | 2020

    Freier Zugriff


    Autonomous Separation Assurance with Deep Multi-Agent Reinforcement Learning

    Brittain, Marc W. / Yang, Xuxi / Wei, Peng | AIAA | 2021