Information processing device, information processing method and program

Abstract

Provided is an information processing apparatus including: a reward estimator generating unit using action history data, which includes state data expressing a state of an agent, action data expressing an agent's action, and a reward value expressing a reward of the action, as learning data to generate, through machine learning, a reward estimator estimating the reward value from inputted state data and action data; an action selecting unit preferentially selecting an action not included in the action history data but with a high estimated reward value; and an action history adding unit causing the agent to perform the selected action and adding to the action history data the state data and action data for the action and the action's reward value in association with each other. The reward estimator is regenerated when a set of state data, action data, and the reward value is added to the action history data.

Description

technical field [0001] The present disclosure relates to an information processing device, an information processing method, and a program. Background technique [0002] In recent years, attention has been paid to methods of mechanically extracting feature quantities from arbitrary datasets whose features are difficult to quantitatively specify. For example, there is known a method for automatically constructing an algorithm for inputting arbitrary music data and mechanically extracting a music genre to which such music data belongs. Music genres such as jazz, classical, and pop are not quantitatively determined by the type of instrument or style of performance. For this reason, it has conventionally been considered difficult to mechanically extract the genre of music data when arbitrary music data is provided. [0003] In reality, however, features that determine the genre of a piece of music are potentially contained in a combination of various information, such as the i...

AI Technical Summary

Problems solved by technology

For this reason, it has conventionally been considered that when arbitrary music data is provided, it is difficult to mechanically extract the genre of music data

Images