Abstract: A process includes obtaining, according to a predetermined update order of a policy parameter of each agent, a degree of influence on a constraint specific to a first agent and a degree of influence on a system-wide constraint in which a degree of influence by an updated policy parameter of a second agent previous to the first agent in the update order is shared, and in a case where an update width of the policy parameter of the first agent exists in both ranges respectively determined depending on the degree of influence on the constraint specific to the first agent and the degree of influence on the system-wide constraint, updating the policy parameter of the first agent and causing the degree of influence on the system-wide constraints by the updated policy parameter to be shared with a third agent next to the first agent in the update order.

Abstract: A non-transitory computer-readable recording medium stores a program for causing a computer to execute a process, the process includes obtaining a third matrix by changing at least one of a position of a target object already installed or a scale of the target object in a two-dimensional second matrix, obtaining three-dimensional second data by superimposing a two-dimensional first matrix and the third matrix, the first matrix being provided for each facility already installed and indicating a position and a scale thereof, and predicting a degree of influence of the target object by inputting the second data, a type of day of week, and time to a machine learning model trained with three-dimensional first data, a type of day of week, and time as input, and with a degree of influence of the target object as output, the first data being obtained by superimposing the first matrix and the second matrix.

Abstract: An electrostatic chuck includes an insulating base body including a predetermined surface, and an electrode inside the base body, which is layer shaped along the predetermined surface. An upper surface of the electrode facing a side where the predetermined surface is located and the base body are in contact. A gap which is rendered a vacuum or filled with a gas is interposed between a side surface of the electrode and the base body.

Abstract: A board-like structure includes a base body, an internal conductor, and a terminal member. The base body is an insulating member including an upper surface and a lower surface on an opposite side to the upper surface. The internal conductor runs along the upper surface and the lower surface inside the base body. The terminal member is at least partially located inside the base body, is exposed to an external portion of the base body at the lower surface, and is electrically connected to the internal conductor. The terminal member includes an insulating terminal base part and a conductor layer on a surfaces of the terminal base part.

Abstract: A heater includes a plate-shaped part, one or more resistance heating element, a columnar part, and a plurality of relay conductors. The plate-shaped part has an insulation property and includes an upper surface on which a wafer is to be superimposed and a lower surface on an opposite side to the upper surface. The one or more resistance heating element is buried in the plate-shaped part. The columnar part has an insulation property and projects downward from the lower surface of the plate-shaped part. The plurality of relay conductors respectively include extension portions vertically extending inside the columnar part and are electrically connected to the one or more resistance heating elements.

Abstract: A non-transitory computer-readable recording medium stores a model generation program for causing a computer to execute a process including: acquiring results output from a first machine learning model in response to input of a first plurality of pieces of data to the first machine learning model; selecting a second plurality of pieces of data from the first plurality of pieces of data, based on the results; and generating a second machine learning model by executing machine learning of the first machine learning model, by using the second plurality of pieces of data as input, with some parameters being fixed among a plurality of parameters included in the first machine learning model.

Abstract: A structural body (2, 2A to 2E) according to the present disclosure includes a base (10, 10D, 10E), a first electrode layer (111), a second electrode layer (112), a first via conductor (131), a second via conductor (132), and a connection conductor (133). The base (10, 10D, 10E) is composed of a ceramic. The first electrode layer (111) and the second electrode layer (112) are located inside the base (10, 10D, 10E). The first via conductor (131) and the second via conductor (132) are located inside the base (10, 10D, 10E) and connect the first electrode layer (111) and the second electrode layer (112). The connection conductor is located inside the base (10, 10D, 10E), and connects the first via conductor and the second via conductor.

Abstract: Structures (2, 2A to 2P) according to the present disclosure have respective bases (10, 10A), electrode layers, and terminals. The bases (10, 10A) are made of a ceramic. The electrode layers (111, 111C, 111D, 111F, 111M, 111N, 111O) are located inside the respective bases (10, 10A). The terminals (41, 41G, 41H, 41I, 41J, 41K, 41L) are electrically connected to the respective electrode layers (111, 111C, 111D, 111F, 111M, 111N, 111O) at respective tip portions of the terminals. Further, the terminals (41, 41G, 41H, 41I, 41J, 41K, 41L) are in contact with the respective electrode layers (111, 111C, 111D, 111F, 111M, 111N, 111O) at respective tip surfaces and side surfaces of the terminals.

Abstract: 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.

Abstract: 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.

Abstract: A heater includes a base, a resistive heating body, and a terminal portion. The base is formed of ceramic and has a plate shape. The resistive heating body is located in the base. The terminal portion is electrically connected to the resistive heating body. The base includes a protruding portion surrounding the terminal portion, on a lower surface side. The protruding portion is formed of a ceramic member, and the terminal portion passes through a through hole formed in the ceramic member. The ceramic member is bonded to at least one of the lower surface of the base or the terminal portion.

Abstract: A creation method that is executed by a computer, the creation method includes acquiring scores representing accuracy of classification of a machine learning model that classifies input data into classes; acquiring a difference in the scores between a first class that has a highest score and a second class that has a next highest score after the first class; and generating a first detection model that determines the classification is undecided when the difference is equal to or less than a first threshold value.

Abstract: A processor generates training data by performing a process, based on a parameter, on first measurement data. The processor trains a machine learning model by using the training data. The processor generates first data by performing the process on second measurement data. The processor generates a first prediction result by entering the first data into the machine learning model, and calculates prediction accuracy based on a label associated with the second measurement data and the first prediction result. The processor changes the parameter of the process in accordance with a comparison between the training data and the first data in response to the predication accuracy being less than a threshold.

Abstract: A detection method for a computer to execute a process includes when data is input to a first detection model among a plurality of detection models trained with boundaries that classify a feature space of data into a plurality of application regions based on a plurality of pieces of training data that corresponds to a plurality of classes, acquiring a first output result that indicates which application region among the plurality of application regions the input data is located in; when data is input to a second detection model, acquiring a second output result; and detecting data that is a factor of an accuracy deterioration of an output result of a trained model based on a time change of data to be data streamed based on the first and the second output result.

Abstract: A creation method for a computer to execute a process includes training a first detection model by using a first training data set; acquiring each of scores of a plurality of pieces of training data included in the first training data set by using the first detection model; creating a second training data set by excluding a part of the training data from the first training data set based on the scores; and training a second detection model by using the second training data set.

Abstract: A base structure includes a base, a first conductor layer, and a via conductor. The base has a first surface. The first conductor layer is positioned along the first surface in the base. The via conductor includes a first part and a second part in a section that includes the via conductor and that extends in a first direction perpendicular to the first surface. The length of the first part in the first direction is larger than the thickness of the first conductor layer. The length of the second part in the first direction is larger than the thickness of the first conductor layer. The second part is continuous with the first part, and at least a portion of the outer edge of the second part is displaced from the outer edge of the first part when viewed in the first direction.

Abstract: A reinforcement learning device includes a processor that determines a first action on a control target by using a basic controller that defines an action on the control target depending on a state of the control target. The processor performs a first reinforcement learning within a first action range around the first action in order to acquire a first policy for determining an action on the control target depending on a state of the control target. The first action range is smaller than a limit action range for the control target. The processor determines a second action on the control target by using the first policy. The processor updates the first policy to a second policy by performing a second reinforcement learning within a second action range around the second action. The second action range is smaller than the limit action range.

Abstract: A heater includes a base body and an internal conductor. The base body is made of ceramic. The internal conductor is located inside the base body and includes a connection portion. The base body includes a space extending from the connection portion to a lower surface of the base body. The space includes a first space and a second space. The first space contacts with the connection portion. The second space connects the first space and an outer side of the lower surface of the base body, and is smaller than the first space in a planar perspective of the lower surface of the base body.

Abstract: A board-like structure includes a base body, an internal conductor, a connection conductor, and a terminal member. The base body is an insulating member including an upper surface and a lower surface on an opposite side to the upper surface. The internal conductor runs along the upper surface and the lower surface inside the base body. The connection conductor is connected to the internal conductor inside the base body. The terminal member is connected to the connection conductor inside the base body and is exposed to an external portion of the base body at the lower surface. The connection conductor is longer in length in a vertical direction than a thickness of the internal conductor in the vertical direction. In the terminal member, at least a side surface is connected to the side surface of the connection conductor.

Abstract: A heater includes a base body, a resistance heating element, and a terminal part. The base body is made of ceramic and is a plate shape. The resistance heating element is located inside the base body. The terminal part is electrically connected to the internal conductor, is located inside the base body in at least a part, and is exposed from a lower surface of the base body to an exterior of the base body. The base body includes a hole opened at the lower surface of the base body. The terminal part includes a connection conductor. The connection conductor is inserted in the hole and is connected to the internal conductor. A lower surface of the connection conductor is located on a side closer to the upper surface of the base body other than the lower surface of the base body. The hole includes a reduced-diameter portion which has a diameter smaller than a diameter of the connection conductor between the lower surface of the connection conductor and the lower surface of the base body.