In this paper, we establish an upper bound on the return gap between the oracle expert policy and an optimal decision tree policy. This enables us to recast the DT extraction problem into a novel non-euclidean clustering problem over the local observation and action values space of each agent, with action values as cluster labels and the upper bound on the return gap as clustering loss.

This makes CDE particularly useful in critical application domains. However, interpretable CDE methods are understudied.

We push each class to its supernode, then apply majority vote to determine the final class.

Neural Information Processing Systems http://nips.cc/

Neural Information Processing Systems http://nips.cc/