The complexity of Markov decision processes
Mathematics of Operations Research
Crytographic limitations on learning Boolean formulae and finite automata
STOC '89 Proceedings of the twenty-first annual ACM symposium on Theory of computing
Navigating in unfamiliar geometric terrain
STOC '91 Proceedings of the twenty-third annual ACM symposium on Theory of computing
The minimum consistent DFA problem cannot be approximated within any polynomial
Journal of the ACM (JACM)
Inference of finite automata using homing sequences
Information and Computation
On complexity as bounded rationality (extended abstract)
STOC '94 Proceedings of the twenty-sixth annual ACM symposium on Theory of computing
Robot navigation with range queries
STOC '96 Proceedings of the twenty-eighth annual ACM symposium on Theory of computing
A Polynominal Time Incremental Algorithm for Learning DFA
ICGI '98 Proceedings of the 4th International Colloquium on Grammatical Inference
How to Explore your Opponent's Strategy (almost) Optimally
ICMAS '98 Proceedings of the 3rd International Conference on Multi Agent Systems
The problem of robot random motion tracking learning algorithms
ISPRA'07 Proceedings of the 6th WSEAS International Conference on Signal Processing, Robotics and Automation
The problem of robot random motion tracking learning algorithms
ISPRA'07 Proceedings of the 6th WSEAS International Conference on Signal Processing, Robotics and Automation
Hi-index | 0.00 |
The paper studies the problem of tracking a target robot by constructing in the observer robot a model of the behaviour of the target. The strategy of the target robot is not known in advance. The algorithm applied is an unsupervised learning algorithm. We make the assumption that the robot motion strategies can be modelled as a finite automata. First we suppose that the observations are noise free and then we relax this constraint to explore the case of a more general case where the observations have some special kind of noise.