Inducing Partially Observable Markov Decision Processes

Michael L. Littman
Proceedings of the Eleventh International Conference on Grammatical Inference, PMLR 21:145-148, 2012.

Abstract

The partially observable Markov decision process (POMDP) model plays an important role in the field of reinforcement learning. It captures the problem of decision making when some important features of the environment are not visible to the decision maker. A number of approaches have been proposed for inducing POMDP models from data, a problem that has important parallels with grammar induction.

Cite this Paper

BibTeX
@InProceedings{pmlr-v21-littman12a, title = {Inducing Partially Observable Markov Decision Processes}, author = {Littman, Michael L.}, booktitle = {Proceedings of the Eleventh International Conference on Grammatical Inference}, pages = {145--148}, year = {2012}, editor = {Heinz, Jeffrey and Higuera, Colin and Oates, Tim}, volume = {21}, series = {Proceedings of Machine Learning Research}, address = {University of Maryland, College Park, MD, USA}, month = {05--08 Sep}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v21/littman12a/littman12a.pdf}, url = {https://proceedings.mlr.press/v21/littman12a.html}, abstract = {The partially observable Markov decision process (POMDP) model plays an important role in the field of reinforcement learning. It captures the problem of decision making when some important features of the environment are not visible to the decision maker. A number of approaches have been proposed for inducing POMDP models from data, a problem that has important parallels with grammar induction.} }
Endnote
%0 Conference Paper %T Inducing Partially Observable Markov Decision Processes %A Michael L. Littman %B Proceedings of the Eleventh International Conference on Grammatical Inference %C Proceedings of Machine Learning Research %D 2012 %E Jeffrey Heinz %E Colin Higuera %E Tim Oates %F pmlr-v21-littman12a %I PMLR %P 145--148 %U https://proceedings.mlr.press/v21/littman12a.html %V 21 %X The partially observable Markov decision process (POMDP) model plays an important role in the field of reinforcement learning. It captures the problem of decision making when some important features of the environment are not visible to the decision maker. A number of approaches have been proposed for inducing POMDP models from data, a problem that has important parallels with grammar induction.
RIS
TY - CPAPER TI - Inducing Partially Observable Markov Decision Processes AU - Michael L. Littman BT - Proceedings of the Eleventh International Conference on Grammatical Inference DA - 2012/08/16 ED - Jeffrey Heinz ED - Colin Higuera ED - Tim Oates ID - pmlr-v21-littman12a PB - PMLR DP - Proceedings of Machine Learning Research VL - 21 SP - 145 EP - 148 L1 - http://proceedings.mlr.press/v21/littman12a/littman12a.pdf UR - https://proceedings.mlr.press/v21/littman12a.html AB - The partially observable Markov decision process (POMDP) model plays an important role in the field of reinforcement learning. It captures the problem of decision making when some important features of the environment are not visible to the decision maker. A number of approaches have been proposed for inducing POMDP models from data, a problem that has important parallels with grammar induction. ER -
APA
Littman, M.L.. (2012). Inducing Partially Observable Markov Decision Processes. Proceedings of the Eleventh International Conference on Grammatical Inference, in Proceedings of Machine Learning Research 21:145-148 Available from https://proceedings.mlr.press/v21/littman12a.html.

Related Material