Learning Human-Understandable Strategies. (arXiv:1612.06340v1 [cs.GT])

Algorithms for equilibrium computation generally make no attempt to ensure that the computed strategies are understandable by humans. For instance the strategies for the strongest poker agents are represented as massive binary files. In many situations, we would like to compute strategies that can actually be implemented by humans, who may have computational limitations and may only be able to remember a small number of features or components of the strategies that have been computed. We study poker games where private information distributions can be arbitrary. We create a large training set of game instances and solutions, by randomly selecting the private information probabilities, and present algorithms that learn from the training instances in order to perform well in games with unseen information distributions. One approach first clusters the training points into a small number of clusters and then creates a small decision tree based on the cluster centers. This approach produces low test error and could be easily implemented by humans since it only requires memorizing a small number of "if-then" rules.

from cs.AI updates on arXiv.org http://ift.tt/2i8WTTK
via IFTTT