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.

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 deep fryer device, the deep fryer device comprising an enclosure delimited by outer walls and a container suitable for containing a liquid, the liquid being preferably an oil, the deep fryer being connected to a filtration system, the filtration system is configured to receive continuously a flow of the liquid in a closed loop configuration, the filtration system comprising a filter element, wherein the filter element is a membrane filter.

Abstract: Capsule for preparing a beverage, in particular a hot beverage, comprising a core material in the form of a compact or a bulk material, wherein the core material is a beverage substance, and a shell encasing the core material, the shell comprising a protein.

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: An installation for treating a gas stream includes: a vessel having an inlet for the gas stream for treatment so as to provide a treated gas stream; an outlet for the treated gas stream; and an adsorbent mass. The vessel is bounded by a double wall defining a peripheral enclosure that surrounds the vessel and that comprises an enclosure inlet and an enclosure outlet for the gas stream for treatment, the enclosure outlet being connected to the inlet of the vessel.

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.