A computer-implemented reinforcement learning method includes determining, based on a target probability of satisfaction of a constraint condition related to a state of a control object and a specific time within which a controller causes the state of the control object not satisfying the constraint condition to be the state of the control object satisfying the constraint condition, a parameter of a reinforcement learner that causes, in a specific probability, the state of the control object to satisfy the constraint condition at a first timing following a second timing at which the state of control object satisfies the constraint condition; and determining a control input to the control object by either the reinforcement learner or the controller, based on whether the state of the control object satisfies the constraint condition at a specific timing.

A reinforcement learning method executed by a computer includes calculating a degree of risk for a state of a controlled object at a current time point with respect to a constraint condition related to the state of the controlled object, the degree of risk being calculated based on a predicted value of the state of the controlled object at a future time point, the predicted value being obtained from model information defining a relationship between the state of the controlled object and a control input to the controlled object; and determining the control input to the controlled object at the current time point, from a range defined according to the calculated degree of risk so that the range becomes narrower as the calculated degree of risk increases.

A control system controls a machine according to a control policy parameterized on a lifted state space of the machine having an unknown onto mapping to a state space of the machine. The control system accepts measurements of state variables that form a portion of the state of the machine and determines a derivative of at least one measured state variable using values of the state variable measured for multiple time instances, such that a combination of the measured state variables and the derivative of the at least one measured state variable defines the lifted state for the time instance. The control system updates the control policy by evaluating a value function of the control policy using the lifted states, such that a control input to the machine is determined using the lifted state and the updated control policy.

The present disclosure provides a system and method for inverse inference in a chain of manufacturing processes using Bayesian networks is provided. The method generates a composite Bayesian network model for a chain of manufacturing processes from Bayesian network models of the unit processes in the chain. The models of unit processes might have been learned independently in other contexts and stored in a knowledge repository. Models relevant for the current problem context are obtained from the knowledge repository and checked for compatibility using ontological information about their inputs and outputs. The obtained compatible Bayesian network models of unit processes are composed to generate a composite Bayesian network model for the chain. The generated composite Bayesian network model is sampled to perform inverse inference.

A control system for controlling a machine includes a controller to control a machine according to a control policy parameterized on a lifted state space of the machine having an unknown onto mapping to a state space of the machine. A state of the machine is an instance in the state space that uniquely defines the machine at a time instance, and a lifted state of the machine is an instance in the lifted state space that defines the machine at the time instance, such that the lifted state space at the time instance has the unknown onto mapping to the state of the machine at the time instance. The control system includes a receiver to accept a sequence of measurements of state variables measured over a sequence of time instances, the state variables measured for the time instance form a portion of the state of the machine at the time instance, a differentiator to determine, for the time instance, a derivative of at least one measured state variable using values of the state variable measured for multiple time instances, such that a combination of the measured state variables and the derivative of the at least one measured state variable defines the lifted state for the time instance, and a processor to update the control policy by evaluating a value function of the control policy using the lifted states, such that the controller determines a control input to the machine using the lifted state and the updated control policy.

A control apparatus for performing predetermined control for a predetermined system using reinforcement learning detects an event in a life cycle of the predetermined system and, in response to the detection of the event, set an exploration parameter specified in accordance with the detected event as a value for adjusting a ratio of exploration in the reinforcement learning. The control apparatus executes the predetermined control using the reinforcement learning in accordance with the set exploration parameter. When a first event is detected, the control apparatus sets the exploration parameter so that makes the ratio of the exploration set during a first period after the first event is smaller than the ratio of the exploration set during a second period before the first event is detected.

A numerical control device for machining a workpiece while performing vibration cutting in which a tool and the workpiece are relatively vibrated by driving a first axis that drives the tool or a second axis that drives the workpiece, includes a parameter adjustment unit that adjust a parameter related to a vibration condition for the vibration cutting, based on the amount of cutting load generated on the first axis or the second axis when the vibration cutting is performed, and a controller that controls the vibration cutting using the adjusted parameter.

An apparatus for printing an energy balance formulation, wherein the apparatus includes at least a processor and a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to receive an energy quantifier related to a user and generate an energy rebalancing plan wherein the energy rebalancing plan identifies an energy balance formulation includes training a machine-learning process using energy training data, wherein the energy training data contains a plurality of inputs containing energy quantifiers correlated to a plurality of outputs containing energy rebalancing plans. The memory containing instructions further configuring the processor to generate the energy rebalancing plan as a function of the machine-learning process and the energy quantifier. The memory containing instructions further configuring the additive manufacturing device to print the energy balance formulation based on the energy rebalancing plan.

An apparatus for printing an energy balance formulation, wherein the apparatus includes at least a processor and a memory communicatively connected to the at least a processor, the memory containing instructions configuring the at least a processor to receive an energy quantifier related to a user and generate an energy rebalancing plan wherein the energy rebalancing plan identifies an energy balance formulation includes training a machine-learning process using energy training data, wherein the energy training data contains a plurality of inputs containing energy quantifiers correlated to a plurality of outputs containing energy rebalancing plans. The memory contains instructions further configuring the processor to generate the energy rebalancing plan as a function of the machine-learning process and the energy quantifier. The memory contains instructions further configuring the additive manufacturing device to print the energy balance formulation based on the energy rebalancing plan.

To provide a numerical control device capable of directly determining whether or not a cutting fluid is applied to a cutting point. A numerical control device includes a determination unit configured to make, on a basis of image data acquired when a vision sensor photographs a cutting fluid jetted from an injection nozzle toward a cutting point, determination of whether or not the cutting fluid is applied to the cutting point, and an instruction unit configured to issue an instruction to a nozzle control device configured to control a position and an attitude of the injection nozzle on a basis of a result of the determination of the determination unit.