Testing probabilistic equivalence through Reinforcement Learning
نویسندگان
چکیده
منابع مشابه
Testing Probabilistic Equivalence Through Reinforcement Learning
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 sugges...
متن کاملTrace Equivalence Characterization Through Reinforcement Learning
In the context of probabilistic verification, we provide a new notion of trace-equivalence divergence between pairs of Labelled Markov processes. This divergence corresponds to the optimal value of a particular derived Markov Decision Process. It can therefore be estimated by Reinforcement Learning methods. Moreover, we provide some PACguarantees on this estimation.
متن کاملTesting Stochastic Processes through Reinforcement Learning
We propose a new approach to verification of probabilistic processes for which the model may not be available. We show how to use a technique from Reinforcement Learning to approximate how far apart two processes are by solving a Markov Decision Process. The key idea of the approach is to define the MDP out of the processes to be tested, in such a way that the optimal value is interpreted as a ...
متن کاملProbabilistic Reasoning through Genetic Algorithms and Reinforcement Learning
In this paper, we develop an efficient approach for inferencing over Bayesian etworks by using a reinforcement learning controller to direct a genetic algorithm. The random variables of a Bayesian network can be grouped into several sets reflecting the strong probabilistic correlations between random variables in the group. We build a reinforcement learning controller to identify these groups a...
متن کاملA Testing Equivalence for Reactive Probabilistic Processes
We consider a generalisation of Larsen and Skou’s [19] reactive probabilistic transition systems which exhibit three kinds of choice: action-guarded probabilistic choice, external (deterministic) and internal (non-deterministic) choice. We propose an operational preorder and equivalence for processes based on testing. Milner’s button pushing experiments scenario is extended with random experime...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: Information and Computation
سال: 2013
ISSN: 0890-5401
DOI: 10.1016/j.ic.2013.02.002