Abstract: A computer-implemented method for for learning a policy. The method includes: recording at least an episode of interactions of the agent with its environment following policy and adding the recorded episode to a set of training data; optimizing a transition dynamics model based on the training data such that the transition dynamics model predicts the next states of the environment depending on the states and actions contained in the training data; optimizing policy parameters based on the training data and the transition dynamics model by optimizing a reward. In the method, the transition dynamics model comprises a first model characterizing the global model and a second model characterizing a correction model, which is configured to correct outputs of the first model.

Abstract: Methods for ascertaining a control strategy for a technical system using a Bayesian optimization method. The control strategy is created based on model parameters of a control model and is executable. The method includes providing a quality function whose shape corresponds to a regression function and that evaluates a quality of a controlling of the technical system based on model parameters; carrying out a Bayesian optimization method based on the quality function in order to iteratively ascertain a model parameter set having model parameters within a model parameter domain that indicates the permissible value ranges for the model parameters; and determining the model parameter domain for at least one of the model parameters as a function of an associated maximum a posteriori estimated value of the quality function.

Abstract: A method is described for selecting evaluation points for a Bayesian optimization method for optimizing a physical or chemical process that is modeled by a statistical model. The method includes the ascertainment of a posterior model of the statistical model in accordance with the results of one or multiple evaluations at previous evaluation points and the selection of a next evaluation point by optimizing an acquisition function over a search space, which is given by a specified limit for the predictive variance of the points in the search space given by the posterior model.

Abstract: A method for optimizing a predefined policy for a robot, the policy being a Gaussian mixture model. The method begins with an initialization of a Gaussian process, the Gaussian process including at least one kernel k which, as an input parameter, obtains a distance that is ascertained between probability distributions, which are characterized in each case by the Gaussian mixture model and the Gaussian process, according to the probability product kernel. This is followed by an optimization of the Gaussian process in such a way that it predicts the costs as a function of the parameters of the Gaussian mixture model. This is followed by an ascertainment of optimal parameters of the Gaussian mixture model as a function of the Gaussian process, the parameters being selected, as a function of the Gaussian process, in such a way that the Gaussian process outputs the optimal cost function.

Abstract: A computer-implemented method for creating a control process for a technical system using a Bayesian optimization method, the control process being created and executable based on model parameters of a control model, the following steps being performed in order to optimize the control process: furnishing a quality function that corresponds to a trainable regression function, and that assesses a quality of a control process of the technical system based on model parameters; executing a Bayesian optimization method based on the quality function in order to iteratively ascertain an optimized model parameter set having model parameters, such that during execution of the Bayesian optimization method, a model parameter domain that indicates the permissible value ranges for the model parameters is expanded, by an amount equal to an expansion distance, with respect to those dimensions for which the model parameter ascertained in the current iteration lies at a range boundary.

Abstract: A computer-implemented method for for learning a policy. The method includes: recording at least an episode of interactions of the agent with its environment following policy and adding the recorded episode to a set of training data; optimizing a transition dynamics model based on the training data such that the transition dynamics model predicts the next states of the environment depending on the states and actions contained in the training data; optimizing policy parameters based on the training data and the transition dynamics model by optimizing a reward. In the method, the transition dynamics model comprises a first model characterizing the global model and a second model characterizing a correction model, which is configured to correct outputs of the first model.

Abstract: Methods for ascertaining a control strategy for a technical system using a Bayesian optimization method. The control strategy is created based on model parameters of a control model and is executable. The method includes providing a quality function whose shape corresponds to a regression function and that evaluates a quality of a controlling of the technical system based on model parameters; carrying out a Bayesian optimization method based on the quality function in order to iteratively ascertain a model parameter set having model parameters within a model parameter domain that indicates the permissible value ranges for the model parameters; and determining the model parameter domain for at least one of the model parameters as a function of an associated maximum a posteriori estimated value of the quality function.

Abstract: A computer-implemented method for creating a control process for a technical system using a Bayesian optimization method, the control process being created and executable based on model parameters of a control model, the following steps being performed in order to optimize the control process: furnishing a quality function that corresponds to a trainable regression function, and that assesses a quality of a control process of the technical system based on model parameters; executing a Bayesian optimization method based on the quality function in order to iteratively ascertain an optimized model parameter set having model parameters, such that during execution of the Bayesian optimization method, a model parameter domain that indicates the permissible value ranges for the model parameters is expanded, by an amount equal to an expansion distance, with respect to those dimensions for which the model parameter ascertained in the current iteration lies at a range boundary.

Abstract: A method for optimizing a predefined policy for a robot, the policy being a Gaussian mixture model. The method begins with an initialization of a Gaussian process, the Gaussian process including at least one kernel k which, as an input parameter, obtains a distance that is ascertained between probability distributions, which are characterized in each case by the Gaussian mixture model and the Gaussian process, according to the probability product kernel. This is followed by an optimization of the Gaussian process in such a way that it predicts the costs as a function of the parameters of the Gaussian mixture model. This is followed by an ascertainment of optimal parameters of the Gaussian mixture model as a function of the Gaussian process, the parameters being selected, as a function of the Gaussian process, in such a way that the Gaussian process outputs the optimal cost function.

Abstract: A method is described for selecting evaluation points for a Bayesian optimization method for optimizing a physical or chemical process that is modeled by a statistical model. The method includes the ascertainment of a posterior model of the statistical model in accordance with the results of one or multiple evaluations at previous evaluation points and the selection of a next evaluation point by optimizing an acquisition function over a search space, which is given by a specified limit for the predictive variance of the points in the search space given by the posterior model.