Incremental evolution of complex general behavior
Adaptive Behavior - Special issue on environment structure and behavior
Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer
Layered Learning in Multiagent Systems: A Winning Approach to Robotic Soccer
Scaling Reinforcement Learning toward RoboCup Soccer
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
Methods for Competitive Co-Evolution: Finding Opponents Worth Beating
Proceedings of the 6th International Conference on Genetic Algorithms
Learning In RoboCup Keepaway Using Evolutionary Algorithms
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Genetic Programming And Multi-agent Layered Learning By Reinforcements
GECCO '02 Proceedings of the Genetic and Evolutionary Computation Conference
Evolving Beharioral Strategies in Predators and Prey
IJCAI '95 Proceedings of the Workshop on Adaption and Learning in Multi-Agent Systems
Keepaway Soccer: A Machine Learning Testbed
RoboCup 2001: Robot Soccer World Cup V
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS
COOPERATIVE COEVOLUTION OF MULTI-AGENT SYSTEMS
Cooperative Coevolution: An Architecture for Evolving Coadapted Subcomponents
Evolutionary Computation
AAMAS '03 Proceedings of the second international joint conference on Autonomous agents and multiagent systems
Emergence of Cooperation: State of the Art
Artificial Life
Evolving explicit opponent models in game playing
Proceedings of the 9th annual conference on Genetic and evolutionary computation
Accelerated Neural Evolution through Cooperatively Coevolved Synapses
The Journal of Machine Learning Research
Collective specialization for evolutionary design of a multi-robot system
SAB'06 Proceedings of the 2nd international conference on Swarm robotics
Coupled inverted pendulums: a benchmark for evolving decentral controllers in modular robotics
Proceedings of the 13th annual conference on Genetic and evolutionary computation
Comparative reproduction schemes for evolving gathering collectives
ECAL'05 Proceedings of the 8th European conference on Advances in Artificial Life
Emergent cooperation in robocup: a review
RoboCup 2005
Evolving team behaviors with specialization
Genetic Programming and Evolvable Machines
Hi-index | 0.00 |
In some complex control tasks, learning a direct mapping from an agent's sensors to its actuators is very difficult. For such tasks, decomposing the problem into more manageable components can make learning feasible. In this paper, we provide a task decomposition, in the form of a decision tree, for one such task. We investigate two different methods of learning the resulting subtasks. The first approach, layered learning, trains each component sequentially in its own training environment, aggressively constraining the search. The second approach, coevolution, learns all the subtasks simultaneously from the same experiences and puts few restrictions on the learning algorithm. We empirically compare these two training methodologies using neuro-evolution, a machine learning algorithm that evolves neural networks. Our experiments, conducted in the domain of simulated robotic soccer keepaway, indicate that neuro-evolution can learn effective behaviors and that the less constrained coevolutionary approach outperforms the sequential approach. These results provide new evidence of coevolution's utility and suggest that solution spaces should not be over-constrained when supplementing the learning of complex tasks with human knowledge.