Comparing a Voting-Based Policy with Winner-Takes-All to Perform Action Selection in Motivational Agents
نویسندگان
چکیده
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 “votingbased” (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.
منابع مشابه
Hospital Choice for Cataract Treatments: The Winner Takes Most
Background Transparency in quality of care is an increasingly important issue in healthcare. In many international healthcare systems, transparency in quality is crucial for health insurers when purchasing care on behalf of their consumers, for providers to improve the quality of care (if necessary), and for consumers to choose their provider in case treatment is needed. Conscious consume...
متن کاملAnalyzing the Performance of "Winner-Take-All" and "Voting-Based" Action Selection Policies within the Two-Resource Problem
The problem of action selection for an autonomous creature implies resolving conflicts between competing behavioral alternatives. These conflicts can be resolved either via competition, following a “winner-take-all” approach, or via cooperation in a “voting-based” approach. In this paper we present two robotic architectures implementing these approaches, and report on experiments we have perfor...
متن کاملComparing a brain-inspired robot action selection mechanism with `winner-takes-all' Benô t Girard
We present a new robotic implementation of a brain-inspired model of action selection described by Gurney et al. (Gurney et al., 2001a, Gurney et al., 2001b) based on neural circuits located in the basal ganglia and thalamus of the vertebrate brain. Compared to an earlier robot implementation (Montes-Gonzalez et al., 2000), the new model demonstrates the capacity of the selection system to prod...
متن کاملArchitectural Mechanisms for the Dynamic Modification of Action Selection Strategies
Action selection is typically a “built-in” feature of agent architectures and hence not subject to change in instantiated architectures. While often (especially in simple agents) this lack of flexibility does not matter, there are circumstances where dynamic adjustments of an action selection strategy are desirable. In this paper, we present an architecture framework, called APOC, that provides...
متن کاملRationalizing Distance Rationalizability
Distance rationalizability is an intuitive paradigm for developing and studying voting rules: given a notion of consensus and a distance function on preference profiles, a rationalizable voting rule selects an alternative that is closest to being a consensus winner. Despite its appeal, distance rationalizability faces the challenge of connecting the chosen distance measure and consensus notion ...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2002