Robust Model Equivalence Using Stochastic Bisimulation for N-Agent Interactive DIDs
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
Text
Chandrasekaran et al. "Robust Model Equivalence Using Stochastic Bisimulation for N-Agent Interactive DIDs." Conference on Uncertainty in Artificial Intelligence, 2017.Markdown
[Chandrasekaran et al. "Robust Model Equivalence Using Stochastic Bisimulation for N-Agent Interactive DIDs." Conference on Uncertainty in Artificial Intelligence, 2017.](https://mlanthology.org/uai/2017/chandrasekaran2017uai-robust/)BibTeX
@inproceedings{chandrasekaran2017uai-robust,
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 = {Conference on Uncertainty in Artificial Intelligence},
year = {2017},
url = {https://mlanthology.org/uai/2017/chandrasekaran2017uai-robust/}
}