Do you even AI, bro? OpenAI Safety Gym enhances reinforcement learning

Elon Musk-founded OpenAI has opened the doors of its "Safety Gym" designed to enhance the training of reinforcement learning agents.

OpenAI describes Safety Gym as "a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety constraints while training."

Basically, Safety Gym is the software equivalent of your spotter making sure you're not going to injure yourself. And just like a good spotter, it will check your...

22 November 2019 | OpenAI

AI enables ‘hybrid drones’ with the attributes of both planes and helicopters

Researchers have developed an AI system enabling ‘hybrid drones’ which combine the attributes of both planes and helicopters.

The propeller-forward designs of most drones are inefficient and reduce flight time. Researchers from MIT, Dartmouth, and the University of Washington have proposed a new hybrid design which aims to combine the perks of both helicopters and fixed-wing planes.

In order to support the new design, a new AI system was developed to switch between...

15 July 2019 | Drones

Uber’s AI beats troublesome games with new type of reinforcement learning

Video games have become a proving ground for AIs and Uber has shown how its new type of reinforcement learning has succeeded where others have failed. Some of mankind’s most complex games, like Go, have failed to challenge AIs from the likes of DeepMind. Reinforcement learning trains algorithms by running scenarios repeatedly with a ‘reward’ given for successes, often a score increase. Two classic games from the 80s – Montezuma’s Revenge and Pitfall! – have thus far been immune to...

27 November 2018 | Reinforcement Learning

Google improves AI model training by open-sourcing framework

Google is helping researchers seeking to train AI models by open-sourcing a reinforcement learning framework used for its own projects. Reinforcement learning has been used for some of the most impressive AI demonstrations thus far, including those which beat human professional gamers at Alpha Go and Dota 2. Google subsidiary DeepMind uses it for its Deep Q-Network (DQN). Building a reinforcement learning framework takes both time and significant resources. For AI to reach its full potential,...

28 August 2018 | Google

AI is helping to make treatment for cancer more bearable

Researchers from MIT are using artificial intelligence to make treatment for cancer less debilitating but just as effective for patients. The AI learns from historical patient data to determine what the lowest doses and frequencies of medication delivered the desired results to shrink tumours. In some cases, the monthly administration of doses was reduced to just twice per year while achieving the same goal. Based on a trial of fifty patients, treatments were reduced to between a quarter and...

13 August 2018 | Healthcare