Abstract | ||
---|---|---|
This paper presents the concept of an autonomous robotic agent combining reactive and machine learning-based algorithms. The focus is on the machine learning-based part that we implement by neural networks. A method for reducing the environment state space to a smaller conceptual world space is given. We then show how the concept of “lifelong learning” can be implemented by neural networks in a robotic action planner |
Year | DOI | Venue |
---|---|---|
1996 | 10.1109/ICNN.1996.549153 | Neural Networks, 1996., IEEE International Conference |
Keywords | Field | DocType |
intelligent control,learning by example,learning systems,neurocontrollers,planning (artificial intelligence),robots,state-space methods,action planner,autonomous robotic agent,conceptual world space,inductive learning,intelligent system,lifelong learning,machine learning,neural networks,reactive learning,robotic agent control,state space,robot control,control systems,artificial intelligence,neural network | Robot learning,Intelligent control,Active learning (machine learning),Evolutionary robotics,Computer science,Hyper-heuristic,Artificial intelligence,Lifelong learning,Artificial neural network,State space | Conference |
Volume | ISBN | Citations |
3 | 0-7803-3210-5 | 0 |
PageRank | References | Authors |
0.34 | 2 | 2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Witold Jacak | 1 | 65 | 13.79 |
Stephan Dreiseitl | 2 | 338 | 34.80 |