Technical Note: \cal Q-Learning
Machine Learning
Artificial intelligence: a modern approach
Artificial intelligence: a modern approach
Exploration in active learning
The handbook of brain theory and neural networks
An Behavior-based Robotics
Human-Level AI's Killer Application: Interactive Computer Games
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Recognition of Human Periodic Motion " A Frequency Domain Approach
ICPR '02 Proceedings of the 16 th International Conference on Pattern Recognition (ICPR'02) Volume 1 - Volume 1
Automated extraction and parameterization of motions in large data sets
ACM SIGGRAPH 2004 Papers
An efficient search algorithm for motion data using weighted PCA
Proceedings of the 2005 ACM SIGGRAPH/Eurographics symposium on Computer animation
Finding repetitive patterns in 3D human motion captured data
Proceedings of the 2nd international conference on Ubiquitous information management and communication
Designing Toys That Come Alive: Curious Robots for Creative Play
ICEC '08 Proceedings of the 7th International Conference on Entertainment Computing
Modelling Behaviour Cycles for Life-Long Learning in Motivated Agents
SEAL '08 Proceedings of the 7th International Conference on Simulated Evolution and Learning
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Motivated Reinforcement Learning: Curious Characters for Multiuser Games
Motivated Reinforcement Learning: Curious Characters for Multiuser Games
Intrinsic Motivation Systems for Autonomous Mental Development
IEEE Transactions on Evolutionary Computation
Hedonic value: enhancing adaptation for motivated agents
Adaptive Behavior - Animals, Animats, Software Agents, Robots, Adaptive Systems
Hi-index | 0.00 |
The behavior of natural systems is governed by rhythmic behavior cycles at the biological, cognitive, and social levels. These cycles permit natural organisms to adapt their behavior to their environment for survival, behavioral efficiency, or evolutionary advantage. This article proposes a model of behavior cycles as the basis for motivated reinforcement learning in developmental robots. Motivated reinforcement learning is a machine learning technique that incorporates a value system with a trial-and-error learning component. Motivated reinforcement learning is a promising model for developmental robotics because it provides a way for artificial agents to build and adapt their skill-sets autonomously over time. However, new models and metrics are needed to scale existing motivated reinforcement learning algorithms to the complex, real-world environments inhabited by robots. This article presents two such models and an experimental evaluation on four Lego Mindstorms NXT robots. Results show that the robots can evolve measurable, structured behavior cycles adapted to their individual physical forms.