M. J. Mataric. Learning in behavior-based multi-robot systems: Policies, models, and other agents. Cognitive Systems Research, 2(1):81--93, Apr 2001. Home/Search Document Details and Download
Summary Related Articles Check |
This paper is cited in the following contexts:
Opportunistically Cooperative Neural Learning in Mobile Agents - Yang, Polycarpou, Minai (2002) (1 citation) (Correct)
....state of its search neighborhood in the near future. Agents do this using feed forward neural networks trained by a reinforcement learning (RL) algorithm [11] Some related methods have been used successfully in robotics and multi agent systems to learn coordination strategies[12] 10] 4] 5] [6]. The goal of the research reported here is to explore two issues: Comparing the performance of a centralized learning (CL) approach, where all agents use the same neural network for their predictions, and a decentralized learning (DL) approach, where each agent has its own, independently ....
M.J. Mataric. Learning in behavior-based multi-robot systems: policies, models, and other agents. Journal of Cognitive System Research, 2(1):81-93, 2001.
Self-Organized Robotic System Design and Autonomous Odor.. - Hayes (Correct)
....produce reliable performance in the presence of sensory noise is dealt with di#erently by the di#erent schools of control that have developed within the robotics field. 2.1. 2 Classes of Control Robotics control can be broken into four divisions: deliberative, reactive, hybrid, and behavior based [71], 2] The di#erences between these approaches stem principally from disagreements over the nature of intelligence whether it stems from extensive cognitive reasoning or from highly tuned and tightly coupled interactions with the environment. Most of the early work in robotics grew out of the ....
.... and sensor noise becomes less of an issue because it can be averaged over many actions [35] However, purely reactive robots also contain no state that might allow them to learn over time, and this inability to adapt has been cited as one of the main shortcomings of this type of control [71]. The purely deliberative and purely reactive strategies represent opposing ends of the control spectrum, and most current work in robotics takes place somewhere in between. One such method, hybrid control, attempts to combine the real time response of reactivity with the rationality and ....
[Article contains additional citation context not shown here]
M. J. Mataric. Learning in behavior-based multi-robot systems: Policies, models, and other agents. Cognitive Systems Research, special issue on Multidisciplinary studies of multi-agent learning, 2(1):81--93, April 2001.
Analysis of a Stochastic Model of Adaptive Task Allocation in .. - Galstyan, Lerman (Correct)
No context found.
M. J. Mataric. Learning in behavior-based multi-robot systems: Policies, models, and other agents. Cognitive Systems Research, 2(1):81--93, Apr 2001.
Online articles have much greater impact More about CiteSeer.IST Add search form to your site Submit documents Feedback
CiteSeer.IST - Copyright Penn State and NEC