From the Google AI Blog. Below just the intro. Something we proposed wayback, but now have seem several interesting examples. Certainly you can consider any interaction with data as a 'game' with goals. So have the game be trained for outcome achievements based upon relevant data and evolving contexts. Here might be a useful start. Berkeley is also doing things of interest.
Quickly Training Game-Playing Agents with Machine Learning
Tuesday, June 29, 2021
Posted by Leopold Haller and Hernan Moraldo, Software Engineers, Google Research
In the last two decades, dramatic advances in compute and connectivity have allowed game developers to create works of ever-increasing scope and complexity. Simple linear levels have evolved into photorealistic open worlds, procedural algorithms have enabled games with unprecedented variety, and expanding internet access has transformed games into dynamic online services. Unfortunately, scope and complexity have grown more rapidly than the size of quality assurance teams or the capabilities of traditional automated testing. This poses a challenge to both product quality (such as delayed releases and post-launch patches) and developer quality of life. ... '
No comments:
Post a Comment