Testing Probabilistic Equivalence Through Reinforcement Learning
- Cite this paper as:
- Desharnais J., Laviolette F., Zhioua S. (2006) Testing Probabilistic Equivalence Through Reinforcement Learning. In: Arun-Kumar S., Garg N. (eds) FSTTCS 2006: Foundations of Software Technology and Theoretical Computer Science. FSTTCS 2006. Lecture Notes in Computer Science, vol 4337. Springer, Berlin, Heidelberg
We propose a new approach to verification of probabilistic processes for which the model may not be available. We use a technique from Reinforcement Learning to approximate how far apart two processes are by solving a Markov Decision Process. If two processes are equivalent, the algorithm will return zero, otherwise it will provide a number and a test that witness the non equivalence. We suggest a new family of equivalences, called K-moment, for which it is possible to do so. The weakest, 1-moment equivalence, is trace-equivalence. The others are weaker than bisimulation but stronger than trace-equivalence.
Unable to display preview. Download preview PDF.