Abstract
Many real-world domains require safe decision making in the presence of uncertainty. In this work, we propose a deep reinforcement learning framework for approaching this important problem. We consider a risk-averse perspective towards model uncertainty through the use of coherent distortion risk measures, and we show that our formulation is equivalent to a distributionally robust safe reinforcement learning problem with robustness guarantees on performance and safety. We propose an efficient implementation that only requires access to a single training environment, and we demonstrate that our framework produces robust, safe performance on a variety of continuous control tasks with safety constraints in the Real-World Reinforcement Learning Suite.
Abstract (translated)
许多现实世界的领域需要在不确定性的情况下安全决策。在这项工作中,我们提出了一个深度强化学习框架,以解决这个问题的重要问题。我们考虑了一种风险厌恶的视角,对模型不确定性采用协调失真风险 measures,并证明我们的框架等于一个分布稳健的安全性强化学习问题,具有表现和安全性的可靠性保证。我们提出了一种高效的实现方法,只需要访问一个训练环境,并证明了我们的框架在真实世界强化学习 Suite中实现具有稳健、安全性的连续控制任务。
URL
https://arxiv.org/abs/2301.12593
