Robert Boschgmbh

Max-planck-gesellschaft Zur Forderung Der Wissenschaften E.v.

Andreas Doerr

Christian Daniel

Felix Berkenkamp

Maksym Lefarov

Sebastian Trimpe

Martin Schiegg

Lukas Froehlich

Valentin Loeffelmann

The Duy Nguyen-Tuong

Michael Volpp

Duy Nguyen-Tuong

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.

Device and method to improve learning of a policy for robots

A method and device parameterize a driving dynamics controller of a vehicle, which intervenes in a controlling manner in a driving dynamics of the vehicle. The driving dynamics controller ascertains an action depending on a vehicle state. The method includes providing a model for predicting a vehicle state. The model configured to predict a subsequent vehicle state depending on the vehicle state and the action. At least one data tuple is ascertained including a sequence of vehicle states and respectively associated actions. The vehicle states are ascertained by the driving dynamics controller using the model depending on an ascertained action. The parameters of the driving dynamics controller are changed/adjusted such that a cost function which ascertains costs of the trajectory depending on the vehicle states and on the ascertained actions of the respectively associated vehicle states and is dependent on the parameters of the driving dynamics controller is minimized.

Method and device for optimum parameterization of a driving dynamics control system for vehicles

A system is described for configuring another system, e.g., a robotics system. The other system interacts with an environment according to a deterministic policy by repeatedly obtaining, from a sensor, sensor data indicative of a state of the environment, determining a current action, and providing, to an actuator, actuator data causing the actuator to effect the current action in the environment. To configure the other system, the system optimizes a loss function based on an accumulated reward distribution with respect to a set of parameters of the policy. The accumulated reward distribution includes an action probability of an action of a previous interaction log being performed according to the current set of parameters. The action probability is approximated using a probability distribution defined by an action selected by the deterministic policy according to the current set of parameters.

Configuring a system which interacts with an environment

A method for ascertaining a time characteristic of a measured variable adjustable by an actuator, wherein a time characteristic of a control variable is applied to the actuator, wherein the ascertaining is effected by means of a Gaussian process state model of the behavior of the actuator, wherein the time characteristic of the measured variable of the actuator is ascertained on the basis of a parameterizable family of functions, wherein in the parameterizable family of functions a time dependency of a later latent state, in particular ascertained using a transfer function, of the actuator on an earlier latent state of the actuator and an earlier control variable of the actuator is the same as the applicable dependency of the Gaussian process state model.

Method for ascertaining a time characteristic of a measured variable, prediction system, actuator control system, method for training the actuator control system, training system, computer program, and machine-readable storage medium

A method for devising an optimum control policy of a controller for controlling a system includes optimizing at least one parameter that characterizes the control policy. A Gaussian process model is used to model expected dynamics of the system. The optimization optimizes a cost function which depends on the control policy and the Gaussian process model with respect to the at least one parameter. The optimization is carried out by evaluating at least one gradient of the cost function with respect to the at least one parameter. For an evaluation of the cost function a temporal evolution of a state of the system is computed using the control policy and the Gaussian process model. The cost function depends on an evaluation of an expectation value of a cost function under a probability density of an augmented state at time steps.

Growing community of inventors

Stuttgart, Germany

Andreas Doerr