Sequential behavior and learning in evolved dynamical neural networks
Adaptive Behavior
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Genetic algorithms + data structures = evolution programs (2nd, extended ed.)
Action-selection in hamsterdam: lessons from ethology
SAB94 Proceedings of the third international conference on Simulation of adaptive behavior : from animals to animats 3: from animals to animats 3
Evolving action selection and selective attention without actions, attention, or selection
Proceedings of the fifth international conference on simulation of adaptive behavior on From animals to animats 5
Recurrent networks: supervised learning
The handbook of brain theory and neural networks
Reinforcement Learning for Biped Locomotion
ICANN '02 Proceedings of the International Conference on Artificial Neural Networks
Evolution of Adaptive Synapses: Robots with Fast Adaptive Behavior in New Environments
Evolutionary Computation
Journal of Cognitive Neuroscience
GECCO'03 Proceedings of the 2003 international conference on Genetic and evolutionary computation: PartI
Evolving reinforcement learning-like abilities for robots
ICES'03 Proceedings of the 5th international conference on Evolvable systems: from biology to hardware
An incremental approach to developing intelligent neural networkcontrollers for robots
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Evolution of Valence Systems in an Unstable Environment
SAB '08 Proceedings of the 10th international conference on Simulation of Adaptive Behavior: From Animals to Animats
Artificial Intelligence Review
Evolving Spiking Neural Parameters for Behavioral Sequences
ICANN '09 Proceedings of the 19th International Conference on Artificial Neural Networks: Part II
Emergence of memory in neuroevolution: impact of selection pressures
Proceedings of the 14th annual conference companion on Genetic and evolutionary computation
| Hi-index | 0.00 |
Temporal and sequential information is essential to any agent continually interacting with its environment. In this paper, we test whether it is possible to evolve a recurrent neural network controller to match the dynamic requirement of the task. As a benchmark, we consider a sequential navigation task where the agent has to alternately visit two rewarding sites to obtain food and water after first visiting the nest. To achieve a better fitness, the agent must select relevant sensory inputs and update its working memory to realize a non-Markovian sequential behavior in which the preceding state alone does not determine the next action. We compare the performance of a feed-forward and recurrent neural control architectures in different environment settings and analyze the neural mechanisms and environment features exploited by the agents to achieve their goal. Simulation and experimental results using the Cyber Rodent robot show that a modular architecture with a locally excitatory recur rent layer outperformed the general recurrent controller.