@inproceedings{bfr-aaai-17,
  author = {Brent Mombourquette and Christian Muise and Sheila McIlraith},
  year = {2017},
  booktitle = {The 31st AAAI Conference on Artificial Intelligence (AAAI)},
  keywords = {state estimation, belief tracking, logical filtering, approximation},
  title = {Logical Filtering and Smoothing: State Estimation in Partially Observable Domains},
  url = {http://www.haz.ca/papers/momb-aaai17.pdf},
  abstract = {State estimation is the task of estimating the state of a partially
observable dynamical system given a sequence of executed
actions and observations. In logical settings, state estimation
can be realized via logical filtering, which is exact
but can be intractable. We propose logical smoothing, a form
of backwards reasoning that works in concert with approximated
logical filtering to refine past beliefs in light of new observations.
We characterize the notion of logical smoothing
together with an algorithm for backwards-forwards state estimation.
We also present an approximation of our smoothing
algorithm that is space efficient. We prove properties of our
algorithms, and experimentally demonstrate their behaviour,
contrasting them with state estimation methods for planning.
Smoothing and backwards-forwards reasoning are important
techniques for reasoning about partially observable dynamical
systems, introducing the logical analogue of effective
techniques from control theory and dynamic programming.}
}

{"_id":"L8fZPGSuDzotdQs33","bibbaseid":"mombourquette-muise-mcilraith-logicalfilteringandsmoothingstateestimationinpartiallyobservabledomains-2017","downloads":2,"creationDate":"2017-03-04T21:09:27.882Z","title":"Logical Filtering and Smoothing: State Estimation in Partially Observable Domains","author_short":["Mombourquette, B.","Muise, C.","McIlraith, S."],"year":2017,"bibtype":"inproceedings","biburl":"https://www.cs.toronto.edu/~sheila/publications/list.bib","bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["Brent"],"propositions":[],"lastnames":["Mombourquette"],"suffixes":[]},{"firstnames":["Christian"],"propositions":[],"lastnames":["Muise"],"suffixes":[]},{"firstnames":["Sheila"],"propositions":[],"lastnames":["McIlraith"],"suffixes":[]}],"year":"2017","booktitle":"The 31st AAAI Conference on Artificial Intelligence (AAAI)","keywords":"state estimation, belief tracking, logical filtering, approximation","title":"Logical Filtering and Smoothing: State Estimation in Partially Observable Domains","url":"http://www.haz.ca/papers/momb-aaai17.pdf","abstract":"State estimation is the task of estimating the state of a partially observable dynamical system given a sequence of executed actions and observations. In logical settings, state estimation can be realized via logical filtering, which is exact but can be intractable. We propose logical smoothing, a form of backwards reasoning that works in concert with approximated logical filtering to refine past beliefs in light of new observations. We characterize the notion of logical smoothing together with an algorithm for backwards-forwards state estimation. We also present an approximation of our smoothing algorithm that is space efficient. We prove properties of our algorithms, and experimentally demonstrate their behaviour, contrasting them with state estimation methods for planning. Smoothing and backwards-forwards reasoning are important techniques for reasoning about partially observable dynamical systems, introducing the logical analogue of effective techniques from control theory and dynamic programming.","bibtex":"@inproceedings{bfr-aaai-17,\n author = {Brent Mombourquette and Christian Muise and Sheila McIlraith},\n year = {2017},\n booktitle = {The 31st AAAI Conference on Artificial Intelligence (AAAI)},\n keywords = {state estimation, belief tracking, logical filtering, approximation},\n title = {Logical Filtering and Smoothing: State Estimation in Partially Observable Domains},\n url = {http://www.haz.ca/papers/momb-aaai17.pdf},\n abstract = {State estimation is the task of estimating the state of a partially\nobservable dynamical system given a sequence of executed\nactions and observations. In logical settings, state estimation\ncan be realized via logical filtering, which is exact\nbut can be intractable. We propose logical smoothing, a form\nof backwards reasoning that works in concert with approximated\nlogical filtering to refine past beliefs in light of new observations.\nWe characterize the notion of logical smoothing\ntogether with an algorithm for backwards-forwards state estimation.\nWe also present an approximation of our smoothing\nalgorithm that is space efficient. We prove properties of our\nalgorithms, and experimentally demonstrate their behaviour,\ncontrasting them with state estimation methods for planning.\nSmoothing and backwards-forwards reasoning are important\ntechniques for reasoning about partially observable dynamical\nsystems, introducing the logical analogue of effective\ntechniques from control theory and dynamic programming.}\n}\n\n","author_short":["Mombourquette, B.","Muise, C.","McIlraith, S."],"key":"bfr-aaai-17","id":"bfr-aaai-17","bibbaseid":"mombourquette-muise-mcilraith-logicalfilteringandsmoothingstateestimationinpartiallyobservabledomains-2017","role":"author","urls":{"Paper":"http://www.haz.ca/papers/momb-aaai17.pdf"},"keyword":["state estimation","belief tracking","logical filtering","approximation"],"metadata":{"authorlinks":{"mcilraith, s":"https://www.cs.toronto.edu/~sheila/publications/index.html","muise, c":"https://www.haz.ca/academic-publications.html"}},"downloads":2},"search_terms":["logical","filtering","smoothing","state","estimation","partially","observable","domains","mombourquette","muise","mcilraith"],"keywords":["state estimation","belief tracking","logical filtering","approximation"],"authorIDs":["GvvCbq8Y4n9QqTySC","f4LpZ8LcDrvDyGuip"],"dataSources":["2LLKDfkxMDdABm58M","euD7cPywCk5gX9zDY","DprwGzu9heN5GXy3u","optQ3PYGE2PxhriFJ","T3oedZczBnZ2Y6GvJ","uKBTF27RvvtN9Ryxw","Jwuh2BtHasSBPk4uf"]}