Ai Dreams Forum
Artificial Intelligence => AI News => Topic started by: infurl on September 01, 2020, 01:27:35 am
-
https://venturebeat.com/2020/08/31/allen-institute-open-sources-allenact-a-framework-for-research-in-embodied-ai/ (https://venturebeat.com/2020/08/31/allen-institute-open-sources-allenact-a-framework-for-research-in-embodied-ai/)
Researchers at the Allen Institute for AI today launched AllenAct, a platform intended to promote reproducible research in embodied AI with a focus on modularity and flexibility. AllenAct, which is available in beta, supports multiple training environments and algorithms with tutorials, pretrained models, and out-of-the-box real-time visualizations.
Knowledge does not equal understanding unless it is grounded, that is, connected to its subject matter so it can interact with it. The most obvious way to build a grounded artificial intelligence is to allow it to interact directly with its environment, but such an embodied AI is very expensive to create and maintain. This new open source library is intended to make that process easier, more efficient, and reproducible.