Abstract: A method for training an agent having a planning component. The method includes carrying out a plurality of control passes, and training the planning component to reduce a loss that includes, for each of a plurality of coarse-scale state transitions occurring in the control passes from a coarse-scale state to a coarse-scale successor state, an auxiliary loss that represents a deviation between a value outputted by the planning component for the coarse-scale state and the sum of a reward received for the coarse-scale state transition and at least a portion of the value of the coarse-scale successor state.

Abstract: A method for controlling a robot. The method includes receiving an indication of a target configuration to be reached from an initial configuration of the robot, determining a coarse-scale value map by value iteration, starting from an initial coarse-scale state and until the robot reaches the target configuration or a maximum number of fine-scale states has been reached, determining a fine-scale sub-goal from the coarse-scale value map, performing, by an actuator of the robot, fine-scale control actions to reach the determined fine-scale sub-goal and obtaining sensor data to determine the fine-scale states reached, starting from a current fine-scale state of the robot and until the robot reaches the determined fine-scale sub-goal, the robot transitions to a different coarse-scale state, or a maximum sequence length of the sequence of fine-scale states has been reached and determining the next coarse-scale state.

Abstract: A method for controlling an agent. The method includes collecting training data for multiple representations of states of the agent; for every representation and using the training data, training a state encoder, a state decoder, an action encoder and an action decoder, and a transition model, shared for the representations, for latent states, and a Q function model, shared by the representations, for latent states; receiving a state of the agent in one of the representations for which a control action is to be ascertained; mapping the state to one or more latent state(s) using the state encoder for the one of the representations; determining Q values for the state(s) for a set of actions using the Q function model; selecting the control action having the best Q value from the set of actions as the control action; and controlling the agent according to the selected control action.

Abstract: A method for controlling an agent. The method includes obtaining numerical values of a first and second set of state variables, which together represent a current full state of the agent, and the numerical values of the first set of state variables represent a current partial state of the robot; determining a state value prior comprising, for potential subsequent partial states following the current partial state, an evaluation of the subsequent partial states in terms of achieving a goal to be attained by the agent; supplying an input comprising a local crop of the state value prior and the numerical values of the second set of state variables representing, together with the numerical values of the first set of state variables, the current full state to a neural network configured to output an evaluation of control actions and controlling the agent in accordance with control signals.

Abstract: A computer-implemented method and device for activating a technical unit. The device includes an input for input data from at least one sensor, an output for activating the technical unit using an activation signal, and a computing device which activates the technical unit as a function of the input data. A state of at least one part of the technical unit or of surroundings is determined as a function of input data. At least one action is determined as a function of the state and of a strategy for the technical unit. Technical unit being activated to carry out the at least one action. The strategy, represented by an artificial neural network, is learned with a reinforcement learning algorithm in interaction with the technical unit or with the surroundings as a function of the at least one feedback signal. The feedback signal is determined as a function of a target-setting.

Abstract: A method for controlling a robot. The method includes receiving an indication of a target configuration to be reached from an initial configuration of the robot, determining a coarse-scale value map by value iteration, starting from an initial coarse-scale state and until the robot reaches the target configuration or a maximum number of fine-scale states has been reached, determining a fine-scale sub-goal from the coarse-scale value map, performing, by an actuator of the robot, fine-scale control actions to reach the determined fine-scale sub-goal and obtaining sensor data to determine the fine-scale states reached, starting from a current fine-scale state of the robot and until the robot reaches the determined fine-scale sub-goal, the robot transitions to a different coarse-scale state, or a maximum sequence length of the sequence of fine-scale states has been reached and determining the next coarse-scale state.