Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding
This addresses safety concerns for reinforcement learning systems in real-world applications, though it is incremental as it builds on existing model-based methods.
The paper tackled the problem of safety-aware reinforcement learning in high-dimensional environments by introducing latent shielding, which uses internal representations to imagine and avoid unsafe trajectories, resulting in improved adherence to safety specifications.
The growing trend of fledgling reinforcement learning systems making their way into real-world applications has been accompanied by growing concerns for their safety and robustness. In recent years, a variety of approaches have been put forward to address the challenges of safety-aware reinforcement learning; however, these methods often either require a handcrafted model of the environment to be provided beforehand, or that the environment is relatively simple and low-dimensional. We present a novel approach to safety-aware deep reinforcement learning in high-dimensional environments called latent shielding. Latent shielding leverages internal representations of the environment learnt by model-based agents to "imagine" future trajectories and avoid those deemed unsafe. We experimentally demonstrate that this approach leads to improved adherence to formally-defined safety specifications.