A generic framework for task selection driven by synthetic emotions
This work addresses task selection in agents without explicit utility functions, but it appears incremental as it builds on existing emotional modeling approaches.
The paper tackles the problem of task selection for humanized agents lacking a credit assignment scheme by proposing a framework based on emotional stationarity, where agents optimize task frequencies to align experienced emotions with a predefined character, resulting in stationary emotion statistics.
Given a certain complexity level, humanized agents may select from a wide range of possible tasks, with each activity corresponding to a transient goal. In general there will be no overarching credit assignment scheme allowing to compare available options with respect to expected utilities. For this situation we propose a task selection framework that is based on time allocation via emotional stationarity (TAES). Emotions are argued to correspond to abstract criteria, such as satisfaction, challenge and boredom, along which activities that have been carried out can be evaluated. The resulting timeline of experienced emotions is then compared with the `character' of the agent, which is defined in terms of a preferred distribution of emotional states. The long-term goal of the agent, to align experience with character, is achieved by optimizing the frequency for selecting the individual tasks. Upon optimization, the statistics of emotion experience becomes stationary.