moon_unit2 writes: The AI technique that DeepMind used to teach machines to play Atari can now bring new video game characters to life. WIRED reports that researchers at Electronic Arts and the University of British Columbia in Canada developed a reinforcement learning method for animating humanoid characters. The approach feeds on data gathered through motion capture, but then uses reinforcement learning…
Tag: reinforcement learning
What’s new on Coursera for Business – February 2020
By Kyle Clark, Senior Skills Transformation Consultant February was a special month at Coursera: we officially launched Rhyme Projects for enterprise. Coursera acquired Rhyme Softworks last year to augment our abilities to create and share hand-on projects with learners. Projects allow learners to work on a task in their browser while following a self-paced or […]
The post What’s new on Coursera…
Facebook Trains An AI To Navigate Without Needing a Map
A team at Facebook AI has created a reinforcement learning algorithm that lets a robot find its way in an unfamiliar environment without using a map. MIT Technology Review reports: Using just a depth-sensing camera, GPS, and compass data, the algorithm gets a robot to its goal 99.9% of the time along a route that is very close to the shortest…
An Algorithm That Learns Through Rewards May Show How Our Brain Does Too
An anonymous reader quotes a report from MIT Technology Review: In a paper published in Nature today, DeepMind, Alphabet’s AI subsidiary, has once again used lessons from reinforcement learning to propose a new theory about the reward mechanisms within our brains. The hypothesis, supported by initial experimental findings, could not only improve our understanding of mental health and motivation. It could…
Microsoft Proposes AI That Improves When You Smile
Positive affectivity, or the characteristic that describes how people experience affects (e.g., sensations, emotions, and sentiments) and interact with others as a result, has been linked to increased interest and curiosity as well as satisfaction in learning. Inspired by this, a team of Microsoft researchers propose imbuing reinforcement learning, an AI training technique that employs rewards to spur systems toward goals,…
Ubisoft Uses AI To Teach a Car To Drive Itself in a Racing Game
An anonymous reader shares a report: Reinforcement learning, an AI training technique that employs rewards to drive software policies toward goals, has been applied successfully to domains from industrial robotics to drug discovery. But while firms including OpenAI and Alphabet’s DeepMind have investigated its efficacy in video games like Dota 2, Quake III Arena, and StarCraft 2, few to date have…