Domain-Independent Heuristics for Goal Formulation (original) (raw)
Related papers
2022
Intelligent physical systems as embodied cognitive systems must perform high-level reasoning while concurrently managing an underlying control architecture. The link between cognition and control must manage the problem of converting continuous values from the real world to symbolic representations (and back). To generate effective behaviors, reasoning must include a capacity to replan, acquire and update new information, detect and respond to anomalies, and perform various operations on system goals. But, these processes are not independent and need further exploration. This paper examines an agent's choices when multiple goal operations co-occur and interact, and it establishes a method of choosing between them. We demonstrate the benefits and discuss the trade offs involved with this and show positive results in a dynamic marine search task.
Why does an Agent Act: Adaptable Motivations for Goal Selection and Generation
We present a framework for active agents, that integrates both the goal achievement desire of traditional A.I. and the survival instinct of new A.I. This framework is based on "motivations" as (1) a control mechanism for internal and external goal selection and (2) a generative mechanism for internal goal generation (usually resulting in one-action plans). We present an architecture and an implementation of the framework, that enables the agent designer to preset the motivational profile of the agent, or the agent itself to change its own motivational profile on the fly, given a priori or perceived knowledge of the environment characteristics. Empirical results involving a mobile robot in various office environments are presented.
A motivation-based approach for Autonomous generation and ranking of goals in artificial agents
2004
A Motivation-based Approach for Autonomous Generation and Ranking of Goals in Artificial Agents Luís Macedo1, 2 1Department of Informatics and Systems Engineering, Engineering Institute, Coimbra Polytechnic Institute R. Pedro Nunes, Quinta da Nora, 3030-199 Coimbra- Portugal lmacedo@ isec. pt Amílcar Cardoso2 2Centre for Informatics and Systems of the University of Coimbra Pinhal de Marrocos, 3030 Coimbra-Portugal {macedo, amilcar}@ dei. uc.
An Intrinsically Motivated Planning Architecture for Curiosity-driven Robots
2019
plans to continuous actions into the real working domain, is well recognised in the literature [1, 4, 6]. However, we have also inserted at the same layer the subsystem (called “KoPro+”, see [8]) for the automatic translation of the newly acquired skills, from a low-level sub-symbolic representation (generated by “GRAIL-IM-Learning”) to a high-level symbolic representation. In some sense, the “KoPro+” module has a dual role in comparison to the Executor; in fact, the learning process can be seen as opposite to the execution process, as it maps low-level sub-symbolic representation into abstract symbolic representation. 3 Operational Evaluation The validation and verification of the IMPACT framework was carried out in the form of two demonstration test cases. The Rover scenario, which demonstrates how the IMPACT system can discover new ways to reach an already known effect by applying the procedure (called KoPro+, see [8]) for the automatic translation of the newly acquired skills fr...