He, Chloe;
Leon, Borja G;
Belardinelli, Francesco;
(2022)
Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding.
In:
Proceedings of the Workshop on Artificial Intelligence Safety 2022 (SafeAI 2022).
ceur-ws.org: Virtual.
Preview |
Text
He_2112.11490.pdf Download (841kB) | Preview |
Abstract
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.
| Type: | Proceedings paper |
|---|---|
| Title: | Do Androids Dream of Electric Fences? Safety-Aware Reinforcement Learning with Latent Shielding |
| Event: | SafeAI 2022 |
| Open access status: | An open access version is available from UCL Discovery |
| Publisher version: | https://ceur-ws.org/Vol-3087/ |
| Language: | English |
| Additional information: | Copyright © 2022 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). |
| UCL classification: | UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science UCL > Provost and Vice Provost Offices > UCL BEAMS > Faculty of Engineering Science > Dept of Computer Science UCL > Provost and Vice Provost Offices > UCL BEAMS UCL |
| URI: | https://discovery.ucl.ac.uk/id/eprint/10143629 |
Loading...
Loading...Loading...Loading...Archive Staff Only
 |
View Item |
