@article{Yang_Simão_Tindemans_Spaan_2021, title={WCSAC: Worst-Case Soft Actor Critic for Safety-Constrained Reinforcement Learning}, volume={35}, url={https://ojs.aaai.org/index.php/AAAI/article/view/17272}, DOI={10.1609/aaai.v35i12.17272}, abstractNote={Safe exploration is regarded as a key priority area for reinforcement learning research. With separate reward and safety signals, it is natural to cast it as constrained reinforcement learning, where expected long-term costs of policies are constrained. However, it can be hazardous to set constraints on the expected safety signal without considering the tail of the distribution. For instance, in safety-critical domains, worst-case analysis is required to avoid disastrous results. We present a novel reinforcement learning algorithm called Worst-Case Soft Actor Critic, which extends the Soft Actor Critic algorithm with a safety critic to achieve risk control. More specifically, a certain level of conditional Value-at-Risk from the distribution is regarded as a safety measure to judge the constraint satisfaction, which guides the change of adaptive safety weights to achieve a trade-off between reward and safety. As a result, we can optimize policies under the premise that their worst-case performance satisfies the constraints. The empirical analysis shows that our algorithm attains better risk control compared to expectation-based methods.}, number={12}, journal={Proceedings of the AAAI Conference on Artificial Intelligence}, author={Yang, Qisong and Simão, Thiago D. and Tindemans, Simon H and Spaan, Matthijs T. J.}, year={2021}, month={May}, pages={10639-10646} }