28 April 2016, USA :
So far people were hitting the gym to stay in shape and get fit but now the time has come that AI systems are going to be trained in the gym! Elon Musk’s OpenAI has created a ‘gym’ to let developers train their AI systems on games and challenges.
The OpenAI Gym, currently in beta, includes environments to simulate situations for AI to learn from, as well as a site to compare and reproduce results.
The tools are designed for use with Reinforcement Learning (RL), one of the technologies used to develop Google’s AlphaGo AI that defeated Go world champion Lee Se-Dol recently. And like you give reward to a dog after finishing it’s job, same way bot will receive a reward every time it completes an action successfully.
The environments available in the OpenAI gym include classic control problems like driving a car up a hill, text -based challenges like learning to win at roulette and 59 Atari games like Asteroids, Air Raid, Pac-Man and Pitfall.
“It’s not just about maximising score; it’s about finding solutions which will generalise well,” a how-to guide from OpenAI explained. “Solutions which involve task-specific hardcoding or otherwise don’t reveal interesting characteristics of learning algorithms are unlikely to pass review.”
OpenAI is a $1 billion non-profit organization dedicated to furthering our understanding of artificial intelligence with a promise to share its research openly with the world.