Induction: processes of inference, learning, and discovery
Induction: processes of inference, learning, and discovery
Real-time control of walking
Learning automata: an introduction
Learning automata: an introduction
Proceedings of the seventh international conference (1990) on Machine learning
Incremental learning of control strategies with genetic algorithms
Proceedings of the sixth international workshop on Machine learning
Learning to Predict by the Methods of Temporal Differences
Machine Learning
Temporal credit assignment in reinforcement learning
Temporal credit assignment in reinforcement learning
Learning in embedded systems
The synthesis of digital machines with provable epistemic properties
TARK '86 Proceedings of the 1986 conference on Theoretical aspects of reasoning about knowledge
A robot that walks; emergent behaviors from a carefully evolved network
Neural Computation
Robotics and Autonomous Systems
Integrated systems based on behaviors
ACM SIGART Bulletin
Learning leg movement patterns using neural oscillators
Proceedings of the 48th Annual Southeast Regional Conference
A biologically inspired approach to feasible gait learning for a hexapod robot
International Journal of Applied Mathematics and Computer Science - Computational Intelligence in Modern Control Systems
A combined reactive and reinforcement learning controller for an autonomous tracked vehicle
Robotics and Autonomous Systems
Autonomous mobile robot control based on white blood cell chemotaxis
CMSB'04 Proceedings of the 20 international conference on Computational Methods in Systems Biology
Learning in behavior-based multi-robot systems: policies, models, and other agents
Cognitive Systems Research
Perceptual control architecture for cyber-physical systems in traffic incident management
Journal of Systems Architecture: the EUROMICRO Journal
Robotics and Autonomous Systems
Sensory integration with articulated motion on a humanoid robot
Applied Bionics and Biomechanics
| Hi-index | 0.00 |
We describe an algorithm which allows a behavior-based robot to learn on the basis of positive and negative feedback when to activate its behaviors. In accordance with the philosophy of behavior-based robots, the algorithm is completely distributed: each of the behaviors independently tries to sensors find out (i) whether it is relevant (i.e. whether it is at all correlated to positive feedback) and (ii) what the conditions are under which it becomes reliable (i.e. the conditions under which it maximises the probability of receiving positive feedback and minimises the probability of receiving negative feedback). The algorithm has been tested successfully on an autonomous 6-legged robot which had to learn how to coordinate its legs so as to walk forward.