• [^] # Re: Nombre de possibilites

    Posté par . En réponse au journal AlphaGo remporte le premier match contre Lee Sedol. Évalué à 7. Dernière modification le 10 mars 2016 à 10:46.

    Cette information est dans la publication dans Nature :

    Evaluating policy and value networks requires several orders of magnitude more computation than traditional search heuristics. To efficiently combine MCTS with deep neural networks, AlphaGo uses an asynchronous multi-threaded search that executes simulations on CPUs, and computes policy and value networks in parallel on GPUs. The final version of AlphaGo used 40 search threads, 48 CPUs, and 8 GPUs. We also implemented a distributed version of AlphaGo that exploited multiple machines, 40 search threads, 1,202 CPUs and 176 GPUs. The Methods section provides full details of asynchronous and distributed MCTS.

    source : http://www.nature.com/nature/journal/v529/n7587/full/nature16961.html

    C'est la version distribuée (1202 CPU et 176 GPU) qui est utilisée dans ce match contre Lee Sedol.