Lookahead planning and latent learning in a classifier system
Proceedings of the first international conference on simulation of adaptive behavior on From animals to animats
Adaptation in natural and artificial systems
Adaptation in natural and artificial systems
Robot sheepdog project achieves automatic flock control
Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Building agent teams using an explicit teamwork model and learning
Artificial Intelligence - Special issue on Robocop: the first step
Artificial Intelligence - Special issue on Robocop: the first step
Artificial Intelligence - Special issue on Robocop: the first step
Genetic Algorithms in Search, Optimization and Machine Learning
Genetic Algorithms in Search, Optimization and Machine Learning
RoboCup-98: Robot Soccer World Cup II
RoboCup-98: Robot Soccer World Cup II
Deliberation Levels in Theoretic-Decision Approaches for Task Allocation in Resource-Bounded Agents
Balancing Reactivity and Social Deliberation in Multi-Agent Systems, From RoboCup to Real-World Applications (selected papers from the ECAI 2000 Workshop and additional contributions)
Reinforcement Learning for Cooperating and Communicating Reactive Agents in Electrical Power Grids
Balancing Reactivity and Social Deliberation in Multi-Agent Systems, From RoboCup to Real-World Applications (selected papers from the ECAI 2000 Workshop and additional contributions)
A Hierarchy of Reactive Behaviors Handles Complexity
Balancing Reactivity and Social Deliberation in Multi-Agent Systems, From RoboCup to Real-World Applications (selected papers from the ECAI 2000 Workshop and additional contributions)
Using Classifier Systems as Adaptive Expert Systems for Control
IWLCS '00 Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems
YACS: Combining Dynamic Programming with Generalization in Classifier Systems
IWLCS '00 Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems
Team Cooperation Using Dual Dynamics
Balancing Reactivity and Social Deliberation in Multi-Agent Systems, From RoboCup to Real-World Applications (selected papers from the ECAI 2000 Workshop and additional contributions)
Intelligence Without Reason
Interaction and intelligent behavior
Interaction and intelligent behavior
Zcs: A zeroth level classifier system
Evolutionary Computation
Classifier fitness based on accuracy
Evolutionary Computation
Using Classifier Systems as Adaptive Expert Systems for Control
IWLCS '00 Revised Papers from the Third International Workshop on Advances in Learning Classifier Systems
Spatial coordination through social potential fields and genetic algorithms
ICSAB Proceedings of the seventh international conference on simulation of adaptive behavior on From animals to animats
| Hi-index | 0.00 |
In the multi-agent community, the need for social deliberation appears contradictory with the need for reactivity. In this paper, we try to show that we can draw the benefits of both being reactive and being socially organized thanks to what we call "social reactivity".In order to defend this claim, we describe a simulation experiment in which several sheepdog agents have to coordinate their effort to drive a flock of ducks towards a goal area. We implement reactive controllers for agents in the Classifier Systems formalism and we compare the performance of purely reactive, solipsistic agents which are coordinated implicitly with the performance of agents using roles. We show that our role-based agents perform better than the solipsistic ones, but because of constraints on the roles of the agents, the solipsistic controllers are more robust and more opportunistic. Then we show that, by exchanging reactively their roles, a process which can be seen as implementing a form of social deliberation, role-based agents finally outperform the solipsistic ones. Since designing by hand the rules for exchanging the roles proved difficult, we conclude by advocating the necessity of tackling the problem of letting the agents learn their own role exchange processes.