Robust Model Equivalence using Stochastic Bisimulation for N-Agent Interactive DIDs

Muthukumaran Chandrasekaran, Junhuan Zhang, Prashant Doshi, Yifeng Zeng
Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, PMLR R15:661-670, 2017.

Abstract

I-DIDs suffer disproportionately from the curse of dimensionality dominated by the exponential growth in the number of models over time. Previous methods for scaling I-DIDs identify notions of equivalence between models, such as behavioral equivalence (BE). But, this requires that the models be solved first. Also, model space compression across agents has not been previously investigated. We present a way to compress the space of models across agents, possibly with different frames, and do so without having to solve them first, using stochastic bisimulation. We test our approach on two non-cooperative partially observable domains with up to 20 agents.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR15-chandrasekaran17a, title = {Robust Model Equivalence using Stochastic Bisimulation for N-Agent Interactive DIDs}, author = {Chandrasekaran, Muthukumaran and Zhang, Junhuan and Doshi, Prashant and Zeng, Yifeng}, booktitle = {Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence}, pages = {661--670}, year = {2017}, editor = {Elidan, Gal and Kersting, Kristian}, volume = {R15}, series = {Proceedings of Machine Learning Research}, month = {11--15 Aug}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r15/main/assets/chandrasekaran17a/chandrasekaran17a.pdf}, url = {https://proceedings.mlr.press/r15/chandrasekaran17a.html}, abstract = {I-DIDs suffer disproportionately from the curse of dimensionality dominated by the exponential growth in the number of models over time. Previous methods for scaling I-DIDs identify notions of equivalence between models, such as behavioral equivalence (BE). But, this requires that the models be solved first. Also, model space compression across agents has not been previously investigated. We present a way to compress the space of models across agents, possibly with different frames, and do so without having to solve them first, using stochastic bisimulation. We test our approach on two non-cooperative partially observable domains with up to 20 agents.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Robust Model Equivalence using Stochastic Bisimulation for N-Agent Interactive DIDs %A Muthukumaran Chandrasekaran %A Junhuan Zhang %A Prashant Doshi %A Yifeng Zeng %B Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2017 %E Gal Elidan %E Kristian Kersting %F pmlr-vR15-chandrasekaran17a %I PMLR %P 661--670 %U https://proceedings.mlr.press/r15/chandrasekaran17a.html %V R15 %X I-DIDs suffer disproportionately from the curse of dimensionality dominated by the exponential growth in the number of models over time. Previous methods for scaling I-DIDs identify notions of equivalence between models, such as behavioral equivalence (BE). But, this requires that the models be solved first. Also, model space compression across agents has not been previously investigated. We present a way to compress the space of models across agents, possibly with different frames, and do so without having to solve them first, using stochastic bisimulation. We test our approach on two non-cooperative partially observable domains with up to 20 agents. %Z Reissued by PMLR on 04 October 2026.
APA
Chandrasekaran, M., Zhang, J., Doshi, P. & Zeng, Y.. (2017). Robust Model Equivalence using Stochastic Bisimulation for N-Agent Interactive DIDs. Proceedings of the 33rd Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R15:661-670 Available from https://proceedings.mlr.press/r15/chandrasekaran17a.html. Reissued by PMLR on 04 October 2026.

Related Material