Deep Reinforcement Learning (DRL) has achieved impressive performance in robotics and autonomous systems (RAS). A key challenge to its deployment in real-life operations is the presence of spuriously unsafe DRL policies. Unexplored states may lead the agent to make wrong decisions that could result in hazards, especially in applications where DRL-trained end-to-end controllers govern the behaviour of RAS. This paper proposes a novel quantitative reliability assessment framework for DRL-controlled RAS, leveraging verification evidence generated from formal reliability analysis of neural networks. A two-level verification framework is introduced to check the safety property with respect to inaccurate observations that are due to, e.g., environmental noise and state changes. Reachability verification tools are leveraged locally to generate safety evidence of trajectories. In contrast, at the global level, we quantify the overall reliability as an aggregated metric of local safety evidence, corresponding to a set of distinct tasks and their occurrence probabilities. The effectiveness of the proposed verification framework is demonstrated and validated via experiments on real RAS.

翻译：深度强化学习（DRL）在机器人及自主系统（RAS）中已取得显著成效。其在实际部署中面临的关键挑战在于存在伪不安全的DRL策略。未探索状态可能导致智能体做出错误决策而引发危险，尤其在DRL训练的端到端控制器主导RAS行为的应用中。本文提出一种针对DRL控制RAS的新型定量可靠性评估框架，该框架利用神经网络形式化可靠性分析生成的验证证据。我们引入两级验证框架，用于检验因环境噪声和状态变化等因素导致的不精确观测下的安全属性。局部层面，利用可达性验证工具生成轨迹的安全证据；全局层面，则将整体可靠性量化为局部安全证据的聚合指标，该指标对应于一组不同任务及其发生概率。通过在真实RAS上的实验，验证了所提框架的有效性。