Bisimulation through probabilistic testing
Information and Computation
The formal semantics of programming languages: an introduction
The formal semantics of programming languages: an introduction
Planning and acting in partially observable stochastic domains
Artificial Intelligence
A Calculus of Communicating Systems
A Calculus of Communicating Systems
Equivalence notions and model minimization in Markov decision processes
Artificial Intelligence - special issue on planning with uncertainty and incomplete information
Metrics for finite Markov decision processes
UAI '04 Proceedings of the 20th conference on Uncertainty in artificial intelligence
Tractable planning under uncertainty: exploiting structure
Tractable planning under uncertainty: exploiting structure
Model minimization in Markov decision processes
AAAI'97/IAAI'97 Proceedings of the fourteenth national conference on artificial intelligence and ninth conference on Innovative applications of artificial intelligence
Belief bisimulation for hidden markov models: logical characterisation and decision algorithm
NFM'12 Proceedings of the 4th international conference on NASA Formal Methods
A Kantorovich-Monadic Powerdomain for Information Hiding, with Probability and Nondeterminism
LICS '12 Proceedings of the 2012 27th Annual IEEE/ACM Symposium on Logic in Computer Science
Exploiting model equivalences for solving interactive dynamic influence diagrams
Journal of Artificial Intelligence Research
| Hi-index | 0.00 |
We explore equivalence relations between states in Markov Decision Processes and Partially Observable Markov Decision Processes. We focus on two different equivalence notions: bisimulation [Givan et al., 2003] and a notion of trace equivalence, under which states are considered equivalent if they generate the same conditional probability distributions over observation sequences (where the conditioning is on action sequences). We show that the relationship between these two equivalence notions changes depending on the amount and nature of the partial observability. We also present an alternate characterization of bisimulation based on trajectory equivalence.