Risk Aversion and Guided Exploration in Safety-Constrained Reinforcement Learning

In traditional reinforcement learning (RL) problems, agents can explore environments to learn optimal policies through trials and errors that are sometimes unsafe. However, unsafe interactions with environments are unacceptable in many safety-critical problems, for instance in robot navigation tasks. Even though RL agents can be trained in simulators, there are many real-world problems without simulators of sufficient fidelity. Constructing safe exploration algorithms for dangerous environments is challenging because we have to optimize policies under the premise of safety. In general, safety is still an open problem that hinders the wider application of RL.