Bisimulation Metric Computation for MDPs

Reasoning and Learning Lab, McGill University, February 2014-February 2015.

Extracting features from Markov decision processes (MDPs) is an important technique for improving the performance of planning algorithms like value iteration. The hope is that if one can extract pertinent features one can plan actions based on these features rather than on detailed knowledge of the state space. In this project, we are using techniques based on probabilistic bisimulation to identify useful features. We want to define a suitable notion of a distance from a state to a feature and use it to identify features. The project involves both theoretical contributions and experimental work.


Related Presentations

Students and professors from McGill Reasoning and Learning Lab at 30th Conference on Uncertainty in Artificial Intelligence (UAI), Quebec City, QC, Canada, July 23-27, 2014

Students and professors from Reasoning and Learning Lab at UAI 2014


Leave a Reply