Artificial Intelligence - Special issue on knowledge representation
Acting optimally in partially observable stochastic domains
AAAI'94 Proceedings of the twelfth national conference on Artificial intelligence (vol. 2)
Issues in temporal reasoning for autonomous control systems
AGENTS '98 Proceedings of the second international conference on Autonomous agents
Managing Temporal Uncertainty Through Waypoint Controllability
IJCAI '99 Proceedings of the Sixteenth International Joint Conference on Artificial Intelligence
Execution of Temporal Plans with Uncertainty
Proceedings of the Seventeenth National Conference on Artificial Intelligence and Twelfth Conference on Innovative Applications of Artificial Intelligence
Strong planning under partial observability
Artificial Intelligence
Probabilistic temporal planning with uncertain durations
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Reasoning about partially observed actions
AAAI'06 Proceedings of the 21st national conference on Artificial intelligence - Volume 1
Temporal dynamic controllability revisited
AAAI'05 Proceedings of the 20th national conference on Artificial intelligence - Volume 3
Dynamic control of plans with temporal uncertainty
IJCAI'01 Proceedings of the 17th international joint conference on Artificial intelligence - Volume 1
A structural characterization of temporal dynamic controllability
CP'06 Proceedings of the 12th international conference on Principles and Practice of Constraint Programming
On the computational complexity of behavioral description-based web service composition
Theoretical Computer Science
Behavioural description based web service composition using abstraction and refinement
International Journal of Web and Grid Services
Hi-index | 0.00 |
We explore a means to both model and reason about partial observability within the scope of constraint-based temporal reasoning. Prior studies of uncertainty in Temporal CSPs have required the realization of all exogenous processes to be made entirely visible to the agent. We relax this assumption and propose an extension to the Simple Temporal Problem with Uncertainty (STPU), one in which the executing agent is made aware of the occurrence of only a subset of uncontrollable events. We argue that such a formalism is needed to encode those complex environments whose external phenomena share a common, hidden source of temporal causality. After characterizing the levels of controllability in the resulting Partially Observable STPU and various special cases, we generalize a known family of reduction rules to account for this relaxation, introducing the properties of extended contingency and sufficient observability. We demonstrate that these modifications enable a polynomial filtering algorithm capable of determining a local form of dynamic controllability; however, we also show that there do remain some instances whose global controllability cannot yet be correctly identified by existing inference rules, leaving the true computational complexity of dynamic controllability an open problem for future research.