Bisimulation through probabilistic testing
Information and Computation
Elements of information theory
Elements of information theory
Introduction to Reinforcement Learning
Introduction to Reinforcement Learning
Metrics for labelled Markov processes
Theoretical Computer Science - Logic, semantics and theory of programming
Predictive state representations: a new theory for modeling dynamical systems
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Planning and acting in partially observable stochastic domains
Artificial Intelligence
Testing probabilistic equivalence through reinforcement learning
FSTTCS'06 Proceedings of the 26th international conference on Foundations of Software Technology and Theoretical Computer Science
Online testing with reinforcement learning
FATES'06/RV'06 Proceedings of the First combined international conference on Formal Approaches to Software Testing and Runtime Verification
Testing probabilistic equivalence through Reinforcement Learning
Information and Computation
| Hi-index | 0.00 |
We propose a new approach for estimating the difference between two partially observable dynamical systems. We assume that one can interact with the systems by performing actions and receiving observations. The key idea is to define a Markov Decision Process (MDP) based on the systems to be compared, in such a way that the optimal value of the MDP initial state can be interpreted as a divergence (or dissimilarity) between the systems. This dissimilarity can then be estimated by reinforcement learning methods. Moreover, the optimal policy will contain information about the actions which most distinguish the systems. Empirical results show that this approach is useful in detecting both big and small differences, as well as in comparing systems with different internal structure.