A hierarchical architecture for behavior-based robots
Proceedings of the first international joint conference on Autonomous agents and multiagent systems: part 1
Heterogeneous Teams of Modular Robots for Mapping and Exploration
Autonomous Robots
Maximizing Reward in a Non-Stationary Mobile Robot Environment
Autonomous Agents and Multi-Agent Systems
ECML '00 Proceedings of the 11th European Conference on Machine Learning
Layered Learning and Flexible Teamwork in RoboCup Simulation Agents
RoboCup-99: Robot Soccer World Cup III
MONAD: a flexible architecture for multi-agent control
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Cooperative Multi-Agent Learning: The State of the Art
Autonomous Agents and Multi-Agent Systems
Balancing Spectral Clustering for Segmenting Spatio-temporal Observations of Multi-agent Systems
ICDM '08 Proceedings of the 2008 Eighth IEEE International Conference on Data Mining
Learning policies for embodied virtual agents through demonstration
IJCAI'07 Proceedings of the 20th international joint conference on Artifical intelligence
Confidence-based robot policy learning from demonstration
Confidence-based robot policy learning from demonstration
Learning multirobot joint action plans from simultaneous task execution demonstrations
Proceedings of the 9th International Conference on Autonomous Agents and Multiagent Systems: volume 1 - Volume 1
A hierarchical protocol for coordinating multiagent behaviors
AAAI'90 Proceedings of the eighth National conference on Artificial intelligence - Volume 1
Hi-index | 0.00 |
We present a supervised learning from demonstration system capable of training stateful and recurrent collective behaviors for multiple agents or robots. A model space of this kind is often high-dimensional and consequently may require a large number of samples to learn. Furthermore, the inverse problem posed by emergent macrophenomena among multiple agents presents major challenges to supervised learning methods. Our approach reduces the size of the state space, and shortens the gap between individual behaviors and macrophenomena, by manually decomposing individual behaviors and arranging the agents into a tree hierarchy. This makes it possible to train potentially large numbers of agents using a small number of samples. We demonstrate our system using hundreds of agents in a simulated foraging task, and on real robots performing a collective patrolling task.