Google DeepMind gamifies memory with its latest AI work

The DeepMind use simulated environments to test how a “reinforcement learning” is able to complete tasks to receive rewards. You know when you’ve done something wrong, like putting a glass too close to the edge of the table, only to accidentally knock it off the table a moment later.

https://www.zdnet.com/article/google-deepmind-gamifies-memory-with-its-latest-ai-work/