Gray hats might have good intentions launching their “vigilante” botnets, but are they really helping us win the war against Death Star-sized thingbots?
Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as good as their training datasets, but in self-play systems, the available data improves automatically as the agent gets better.
We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the game from scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.
With “thingbots” now launching Death Star-sized DDoS attacks, hosting banking trojans, and causing physical destruction, all signs point to them becoming the attacker infrastructure of the future.
With “thingbots” now launching Death Star-sized DDoS attacks, hosting banking trojans, and causing physical destruction, all signs point to them becoming the attacker infrastructure of the future.
With “thingbots” now launching Death Star-sized DDoS attacks, hosting banking trojans, and causing physical destruction, all signs point to them becoming the attacker infrastructure of the future.