Thiago D. Simão, Nils Jansen 0001, Matthijs T. J. Spaan. AlwaysSafe: Reinforcement Learning without Safety Constraint Violations during Training. In Frank Dignum, Alessio Lomuscio, Ulle Endriss, Ann Nowé, editors, AAMAS '21: 20th International Conference on Autonomous Agents and Multiagent Systems, Virtual Event, United Kingdom, May 3-7, 2021. pages 1226-1235, ACM, 2021. [doi]
Abstract is missing.