We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal performance. ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.
Gray hats might have good intentions launching their “vigilante” botnets, but are they really helping us win the war against Death Star-sized thingbots?
Gray hats might have good intentions launching their “vigilante” botnets, but are they really helping us win the war against Death Star-sized thingbots?
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.