Abstract: A computer-implemented method for training a machine learning system. The machine learning system is configured to determine a control signal characterizing an action to be executed by a technical system. The method includes obtaining a safe action to be executed by the technical system including: obtaining a state signal; determining, by a parametrized policy module of the machine learning system, a distribution of potentially unsafe actions that could be executed by the technical system; sampling a potentially unsafe action from the distribution; obtaining, by a safety module of the machine learning system, the safe action. The method further includes determining a loss value based on the state signal and the safe action; and training the machine learning system by updating parameters of the policy module according to a gradient of the loss value with respect to the parameters.

Abstract: A device and method for controlling a hardware agent in a control situation having a plurality of hardware agents. The method includes ascertaining of a potential function by a first neural network; ascertaining of a control scenario for a control situation from a plurality of possible control scenarios by a second neural network; ascertaining a common action sequence for the plurality of hardware agents by seeking an optimum of the ascertained potential function over the possible common action sequences of the ascertained control scenario; and controlling at least one of the plurality of hardware agents in accordance with the ascertained common action sequence.

Abstract: A computer-implemented method for performing Learning from Demonstrations, particularly Imitation Learning, based on data associated with a first domain, particularly a source domain. The method includes: determining first data characterizing a demonstrator of the first domain, wherein particularly the first data characterizes sensor data of the demonstrator and/or sensor data of at least one spectator observing the demonstrator, determining first knowledge from the first domain based on the first data, transferring at least a part of the first knowledge to a second domain, particularly a target domain.