ACKTR can learn continuous control tasks, like moving a robotic arm to a target location, purely from low-resolution pixel inputs (left). ACKTR (pronounced "actor") -- Actor Critic using Kronecker-factored Trust Region -- was developed by researchers at the University of Toronto and New York University, and we at OpenAI have collaborated with them to release a Baselines implementation. The authors use ACKTR to learn control policies for simulated robots (with pixels as input, and continuous action spaces) and Atari agents (with pixels as input and discrete action spaces). ACKTR combines three distinct techniques: actor-critic methods, trust region optimization for more consistent improvement, and distributed Kronecker factorization to improve sample efficiency and scalability. For machine learning algorithms, two costs are important to consider: sample complexity and computational complexity.

Tesla CEO Elon Musk fired off a new and ominous warning on Friday about artificial intelligence, suggesting the emerging technology poses an even greater risk to the world than a nuclear conflagration with North Korea. Musk--a fierce and long time critic of A.I. who once likened it to "summoning the demon" in a horror movie--said in a Twitter post that people should be concerned about the rise of the machines than they are. Reacting to the news that autonomous tech had bested competitive players in an electronic sports competition, Musk posted what appeared to be a photo of a poster bearing the chilling words "In the end, the machines will win." Musk, who is spearheading commercial space travel with his venture SpaceX, is also the founder of OpenAI, a nonprofit that promotes the "safe" development of AI. His stance puts him at odds with much of the tech industry, but echoes remarks of prominent voices like Stephen Hawking--who has also issued dire warnings about machine learning.

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. Improvements came from every part of the system, from adding new features to algorithmic improvements to scaling things up. The graph is surprisingly linear, meaning the team improved the bot exponentially over time.

The bot by OpenAI demonstrated its skills at the annual live tournament "The International" this past weekend. It was up against a crowd favorite, the pro player "Dendi" who is one of the best in the world when it comes to Dota 2. He was defeated by the bot twice, before forfeiting any more future matches. After the game, Dendi stated that the bot "feels a little like [a] human, but a little like something else." - many of its moves looked familiar and human. He was surprised that it was possible for the AI machine to beat a human player - and therefore human intelligence. 'Bot is really fun and challenging to play against.

By Cade Metz SAN FRANCISCO: At OpenAI, the artificial intelligence lab founded by Tesla's chief executive, Elon Musk, machines are teaching themselves to behave like humans. But sometimes, this goes wrong. Sitting inside OpenAI's San Francisco offices on a recent afternoon, the researcher Dario Amodei showed off an autonomous system that taught itself to play Coast Runners, an old boat-racing video game. The winner is the boat with the most points that also crosses the finish line. The result was surprising: The boat was far too interested in the little green widgets that popped up on the screen.

For decades, the world's smartest game-playing humans have been racking up losses to increasingly sophisticated forms of artificial intelligence. The defeats began in the 1990s when IBM's Deep Blue computer conquered chess master Garry Kasparov. More recently, Ke Jie -- until then the world's best player of the ancient Chinese board game "Go" -- was defeated by a Google computer program in May. Now the AI supergamers have moved into the world of e-sports. Last week, an artificial intelligence bot created by the Elon Musk-backed start-up OpenAI defeated some of the world's most talented players of Dota 2, a fast-paced, highly complex, multiplayer online video game that draws fierce competition from all over the globe.

You might not have noticed, but over the weekend a little coup took place. On Friday night, in front of a crowd of thousands, an AI bot beat a professional human player at Dota 2 -- one of the world's most popular video games. The human champ, the affable Danil "Dendi" Ishutin, threw in the towel after being killed three times, saying he couldn't beat the unstoppable bot. "It feels a little bit like human," said Dendi. The bot's patron was none other than tech billionaire Elon Musk, who helped found and fund the institution that designed it, OpenAI.

Today we played Dendi on mainstage at The International, winning a best-of-three match. Over the past week, our bot was undefeated against many top professionals including SumaiL (top 1v1 player in the world) and Arteezy (top overall player in the world). Dota 1v1 is a complex game with hidden information. Agents must learn to plan, attack, trick, and deceive their opponents. The correlation between player skill and actions-per-minute is not strong, and in fact, our AI's actions-per-minute are comparable to that of an average human player.

Elon Musk is a hype merchant, and this weekend his Twitter account served up a generous serving of hoopla for the OpenAI bots that were destroying the best Dota 2 players in the world. As a veteran Dota player and inveterate contrarian, I couldn't let Musk's exaggeration go by unchallenged. What we saw the OpenAI bots achieve was awe-inspiring for anyone who's ever dabbled in Dota, but it's still only scratching the surface of the competitive complexity of this game. OpenAI first ever to defeat world's best players in competitive eSports. Vastly more complex than traditional board games like chess & Go.

Elon Musk has warned again about the dangers of artificial intelligence, saying that it poses "vastly more risk" than the apparent nuclear capabilities of North Korea does. The Tesla and SpaceX chief executive took to Twitter to once again reiterate the need for concern around the development of AI, following the victory of Musk-led AI development over professional players of the Dota 2 online multiplayer battle game. If you're not concerned about AI safety, you should be. This is not the first time Musk has stated that AI could potentially be one of the most dangerous international developments. He said in October 2014 that he considered it humanity's "biggest existential threat", a view he has repeated several times while making investments in AI startups and organisations, including OpenAI, to "keep an eye on what's going on".