Abstract: A data processing device includes a state value calculation unit which calculates a state value of which the value increases as much as a state with a high transition probability for each state of the state transition model, an action value calculation unit which calculates an action value, of which the value increases as a transition probability increases for each state of the state transition model and each action that the agent can perform, a target state setting unit which sets a state with great unevenness in the action value among states of the state transition model to a target state that is the target to reach by action performed by the agent, and an action selection unit which selects an action of the agent so as to move toward the target state.

Abstract: An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability bas

Abstract: An information processing device includes: a learning section configured to learn a state transition probability model defined by state transition probability for each action of a state making a state transition due to an action performed by an agent capable of performing action and observation probability of a predetermined observed value being observed from the state, using an action performed by the agent and an observed value observed in the agent when the agent has performed the action.

Abstract: A robot can make a dialog customized for the user by first storing various pieces of information appendant to an object as values of the corresponding items of the object. A topic that is related to the topic used in the immediately preceding conversation is then selected. Then, an acquisition conversation for acquiring the value of the item of the selected topic or a utilization conversation for utilizing the value of the item of the topic that is already stored is generated as the next conversation. The value acquired by the acquisition conversation is stored as the value of the corresponding item.

Abstract: A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.

Abstract: An HMM (Hidden Markov Model) learning device includes: a learning unit for learning a state transition probability as the function of actions that an agent can execute, with learning with HMM performed based on actions that the agent has executed, and time series information made up of an observation signal; and a storage unit for storing learning results by the learning unit as internal model data including a state-transition probability table and an observation probability table; with the learning unit calculating frequency variables used for estimation calculation of HMM state-transition and HMM observation probabilities; with the storage unit holding the frequency variables corresponding to each of state-transition probabilities and each of observation probabilities respectively, of the state-transition probability table; and with the learning unit using the frequency variables held by the storage unit to perform learning, and estimating the state-transition probability and the observation probability bas

Abstract: An information processing device includes: a calculating unit configured to calculate a current-state series candidate that is a state series for an agent capable of actions reaching the current state, based on a state transition probability model obtained by performing learning of the state transition probability model stipulated by a state transition probability that a state will be transitioned according to each of actions performed by an agent capable of actions, and an observation probability that a predetermined observation value will be observed from the state, using an action performed by the agent, and an observation value observed at the agent when the agent performs an action; and a determining unit configured to determine an action to be performed next by the agent using the current-state series candidate in accordance with a predetermined strategy.

Abstract: An information processing device includes: a learning section configured to learn a state transition probability model defined by state transition probability for each action of a state making a state transition due to an action performed by an agent capable of performing action and observation probability of a predetermined observed value being observed from the state, using an action performed by the agent and an observed value observed in the agent when the agent has performed the action.

Abstract: An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.

Abstract: An information processing apparatus including a learning unit that learns a predetermined time-series pattern. An output unit outputs a time-series pattern corresponding to the result of learning by the learning unit. An adjusting unit supplied with a time-series pattern obtained from an action by an action unit on the basis of a time-series pattern supplied from the output unit and external teaching for the action adjusts a time-series pattern supplied from the output unit correspondingly to the input time-series pattern. The learning unit learns the time-series pattern supplied from the output unit and adjusted by the adjusting unit.

Abstract: A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.

Abstract: A learning apparatus includes a storage unit configured to store a network formed by a plurality of nodes each holding dynamics; a learning unit configured to learn the dynamics of the network in a self-organizing manner on the basis of observed time-series data; a winner-node determiner configured to determine a winner node, the winner node being a node having dynamics that best match the time-series data; and a weight determiner configured to determine learning weights for the dynamics held by the individual nodes according to distances of the individual nodes from the winner node. The learning unit is configured to learn the dynamics of the network in a self-organizing manner by degrees corresponding to the learning weights.

Abstract: An information processing apparatus includes a storage unit configured to store a node holding dynamics; an input-weight-coefficient adjuster configured to adjust input-weight coefficients on a dimension-by-dimension basis, the input-weight coefficients being weight coefficients for individual dimensions of input data input to input units of the node, the input data being observed time-series data having a plurality of dimensions; and an output-weight-coefficient adjuster configured to adjust output-weight coefficients on a dimension-by-dimension basis, the output-weight coefficients being weight coefficients for individual dimensions of output data having a plurality of dimensions and output from output units of the node.

Abstract: Teaching to a robot for an action on an external object can be made easily and efficiently. According to the present invention, there is provided an information processing apparatus including a learning unit for learning a predetermined time-series pattern, an output unit for outputting a time-series pattern corresponding to the result of learning by the learning unit, and an adjusting unit supplied with a time-series pattern obtained from an action made by an action unit on the basis of a time-series pattern supplied from the output unit and external teaching for the action to adjust a time-series pattern supplied from the output unit correspondingly to the input time-series pattern, the learning unit learning the time-series pattern supplied from the output unit and adjusted by the adjusting unit.

Abstract: A learning system is provided, which includes network storage means for storing a network including a plurality of nodes, each of which holds a dynamics; and learning means for self-organizationally updating the dynamics of the network on the basis of measured time-series data.

Abstract: A robot (1) is provided which includes a situated behaviors layer (SBL) (58). This SBL (58) is formed in the form of a tree structure in which a plurality of schemata (behavior modules) is connected hierarchically in such a matter that the schemata are highly independent of each other for each of them to behave uniquely. A patent schema can define a pattern in which child schemata are connected, such as an OR type pattern in which the child schemata are caused to behave uniquely, AND type pattern in which the plurality of child schemata are caused to behave simultaneously or a SEQUENCE type pattern indicating a sequence in which the plurality of child schemata should behave, thereby permitting to select a behavior pattern of the robot (1). Also, a new child schema can additionally be included in the SBL (58) without having to rewrite the schemata connection in the tree structure, whereby a new behavior or function can be added to the robot (1).

Abstract: No robot that can make a dialog customized for the user is known to date. According to the invention, various pieces of information appendant to an object are stored as values of the corresponding items of the object and a topic that is related to the topic used in the immediately preceding conversation is selected. Then, an acquisition conversation for acquiring the value of the item of the selected topic or a utilization conversation for utilizing the value of the item of the topic that is already stored is generated as the next conversation. The value acquired by the acquisition conversation is stored as the value of the corresponding item.

Abstract: A behavior control system and a behavior control method for a robot apparatus are disclosed. The behavior control system and the behavior control method for a robot apparatus include a function of adaptively switching between a behavior selection standard, taking into account the own state, required of an autonomous robot, and a behavior selection standard, taking into account the state of a counterpart, responsive to a situation. A behavior selection control system in a robot apparatus includes a situation-dependent behavior layer (SBL), capable of selecting a particular behavior from plural behaviors, and outputting the so selected behavior, and an AL calculating unit 120 for calculating the AL (activation level), indicating the priority of execution of the behaviors, for behavior selection.

Abstract: A robot (1) is provided which includes a situated behaviors layer (SBL) (58). This SBL (58) is formed in the form of a tree structure in which a plurality of schemata (behavior modules) is connected hierarchically in such a matter that the schemata are highly independent of each other for each of them to behave uniquely. A patent schema can define a pattern in which child schemata are connected, such as an OR type pattern in which the child schemata are caused to behave uniquely, AND type pattern in which the plurality of child schemata are caused to behave simultaneously or a SEQUENCE type pattern indicating a sequence in which the plurality of child schemata should behave, thereby permitting to select a behavior pattern of the robot (1). Also, a new child schema can additionally be included in the SBL (58) without having to rewrite the schemata connection in the tree structure, whereby a new behavior or function can be added to the robot (1).