Google is open-sourcing its flagship AI 3D platform for agent-based AI research, DeepMind Lab.
“DeepMind’s scientific mission is to push the boundaries of AI, developing systems that can learn to solve any complex problem without needing to be taught how,” the DeepMind team wrote in a blog post. “To achieve this, we work from the premise that AI needs to be general. Agents should operate across a wide range of tasks and be able to automatically adapt to changing circumstances.”
(Related: DeepMind AI can learn from its own memory)
According to Google, the research done at DeepMind has been to develop intelligent agents with advanced cognitive skills, as well as providing an environment where those agents can be trained and analyzed. Those simulated environments are meant to be AI labs for research.
“Artificial general intelligence research in DeepMind Lab emphasizes navigation, memory, 3D vision from a first-person viewpoint, motor control, planning, strategy, time, and fully autonomous agents that must learn for themselves what tasks to perform by exploring their environment,” the team wrote.
Researchers can also take advantage of the lab’s programmatic level-creation interfaces. The customizable levels can include gameplay logic, observations and the ability to pick up items.
DeepMind Lab, along with its code, maps and level scripts, will be available on GitHub. “Our hope is that the community will help us shape and develop the platform going forward,” the team wrote.