Reinforcement learning: how computers learn from experience

(OpenAI)

Reinforcement learning is a form of AI training that allows a program to explore an environment and learn from its experiences.

It's used in self-driving cars, wherein the software learns how to lane merge safely after driving the same simulated roads many, many times.

It's also used in games. Instead of writing complicated instructions, programmers set an AI loose to play itself inside board games like Go, Chess, and Bakgammon, and multiplayer games like Starcraft. In some instances, like OpenAI's quest to teach an AI to play the video game Dota 2, the AIs played an equivalent of 180 years per day in order to learn and play well.

In some cases, the best practices AIs develop through reinforcement look very different from human play.

Sections

OpenAI

August 11th

OpenAI was founded as a non-profit research lab by Elon Musk and Sam Altman in 2015.

In February, 2018, Musk left, citing a conflict of interest with his work on Tesla's autopilot system.

In 2019, with Altman in charge, OpenAI formed OpenAI LP, a for-profit company it wrote will allow them "to rapidly increase our investments in compute and talent while including checks and balances to actualize our mission."

OpenAI has produced some impressive accomplishments-- in early 2019, its neural networks beat the world's best Dota 2 players. And in July, Microsoft invested $1 billion in OpenAI to pursue artificial general intelligence, an accomplishment many think is atill decades away, if not longer.