Unity Technologies released the open beta version of its Unity Machine Learning Agents, an artificial intelligence toolkit developers and researchers can use to virtually train agents —whether video game characters, autonomous vehicles or robots.
“Machine learning is a disruptive technology that is important to all types of developers and researchers to make their games or systems smarter, but complexities and technical barriers make it out of reach for most,” vice president of AI and machine learning Danny Lange said in a press release. “This is an exciting new chapter in AI’s history as we are making an end-to-end machine learning environment widely accessible, and providing the critical tools needed to make more intelligent, beautiful games and applications. Complete with Unity’s physics engine and a 3D photorealistic rendering environment, our AI toolkit also offers a game-changing AI research platform to a rapidly growing community of AI enthusiasts exploring the frontiers of Deep Learning.”
The open source toolkit makes the technology to train intelligent agents much for widely available. The reinforcement learning technique used in the toolkit lets machines learn and develop based on trail-and-error and the related rewards and punishments of certain actions, eliminating some of the time needed to code and program the agents.
For robots, the platform presents a virtual environment where machines can learn. For example, developers can work on autonomous vehicles in a realistic online arena before introducing them to the actual road. The toolkit though is versatile enough that academic and industry researchers can adapt and use it for their different purposes and projects.