1. Constrained policy optimization;Achiam,2017
2. Towards safe reinforcement learning in the real world;Ahn,2019
3. Safe reinforcement learning via shielding;Alshiekh,2018
4. Amodei, D., Olah, C., Steinhardt, J., Christiano, P. F., Schulman, J., & Mané, D. (2016). Concrete problems in AI safety. CoRR abs/1606.06565.
5. Deep RL for autonomous robots: limitations and safety challenges;Andersson,2019