Parallel evaluation of neural game value networks

Abstract text:

Parallel evaluation of neural game value networks

István Borsos1

1 Institute for Technical Physics and Materials Science, Centre for Energy Research, Hungarian Academy of Sciences, P.O. Box 49, H-1525 Budapest, Hungary

During minimax evaluation of nodes of game value networks, a number of follow-up moves are generated and the values of the resulting positions are predicted by the network in order to compute a better estimation for the value of the original position. In parallel implementation of this problem multiple nodes (several hundreds when using a GPU) should be evaluated simultaneously, but the different number of follow-up moves or the early exits (like e.g. alpha cut-os) during the investigation of some of the nodes makes the direct parallelization less efficient. In this talk, we present a method to improve the efficiency of this computation.

István Borsos

End of talk: 6/22/2018 10:20:00 AM

Start of talk: 6/22/2018 10:00:00 AM