🚀 Feature Request
Part of #42. Depends on #48. With an agent running a learned policy, and training in a visualization platform, we should experiment with implementing online learning in our agent so that it can learn while playing matches, whether in the visualization platform, or in the not-so-distant future during real tournament play.
🚀 Feature Request
Part of #42. Depends on #48. With an agent running a learned policy, and training in a visualization platform, we should experiment with implementing online learning in our agent so that it can learn while playing matches, whether in the visualization platform, or in the not-so-distant future during real tournament play.