Comparing a Voting-Based Policy with Winner-Takes-All to Perform Action Selection in Motivational Agents
| Title | Comparing a Voting-Based Policy with Winner-Takes-All to Perform Action Selection in Motivational Agents |
| Publication Type | Conference Paper |
| Year of Publication | 2002 |
| Authors | Avila-García, O, Cañamero, L |
| Editor | Garijo, FJ, Riquelme, JC, Toro, M |
| Name of Proceedings | Advances in Artificial Intelligence – IBERAMIA 2002; Proc. 8th Ibero-American Conference on AI |
| Series Title | Lecture Notes in Computer Science |
| Series Volume | 2527 |
| Pagination | 855–864 |
| Publisher | Springer |
| Conference Location | Seville, Spain |
| ISBN Number | 978-3-540-00131-7 |
| Abstract | Embodied autonomous agents are systems that inhabit dynamic, unpredictable environments in which they try to satisfy a set of time-dependent goals or motivations in order to survive. One of the problems that this implies is action selection, the task of resolving conflicts between competing behavioral alternatives. We present an experimental comparison of two action selection mechanisms (ASM), implementing "winner-takes-all" (WTA) and "voting-based" (VB) policies respectively, modeled using a motivational behavior-based approach. This research shows the adequacy of these two ASM with respect to different sources of environmental complexity and the tendency of each of them to show different behavioral phenomena. |
| DOI | 10.1007/3-540-36131-6_87 |