Sciweavers

4597 search results - page 811 / 920
» The Spider Model of Agents
Sort
View
ECAI
2008
Springer
13 years 9 months ago
Exploiting locality of interactions using a policy-gradient approach in multiagent learning
In this paper, we propose a policy gradient reinforcement learning algorithm to address transition-independent Dec-POMDPs. This approach aims at implicitly exploiting the locality...
Francisco S. Melo
EUROS
2008
153views Robotics» more  EUROS 2008»
13 years 9 months ago
Adaptive Multiple Resources Consumption Control for an Autonomous Rover
Resources consumption control is crucial in the autonomous rover context. Most of the time, the resources consumption is probabilistic. During execution time, the rover has to adap...
Simon Le Gloannec, Abdel-Illah Mouaddib, Fran&cced...
DAGSTUHL
2007
13 years 9 months ago
Spatially Distributed Normative Objects
Organisational structures for multi-agent systems are usually defined independently of any spatial and temporal structure. Therefore, when the multi-agent system is situated in a ...
Fabio Y. Okuyama, Rafael H. Bordini, Antônio...
DAGSTUHL
2007
13 years 9 months ago
Learning Probabilistic Relational Dynamics for Multiple Tasks
The ways in which an agent’s actions affect the world can often be modeled compactly using a set of relational probabilistic planning rules. This paper addresses the problem of ...
Ashwin Deshpande, Brian Milch, Luke S. Zettlemoyer...
HCI
2007
13 years 9 months ago
Augmented Metacognition Addressing Dynamic Allocation of Tasks Requiring Visual Attention
This paper discusses the use of cognitive models as augmented metacognition on task allocation for tasks requiring visual attention. In the domain of naval warfare, the complex and...
Tibor Bosse, Willem A. van Doesburg, Peter-Paul va...