Google Tested Its AI Tutor In Real Classrooms. It Worked

Google says its AI tutor delivered a year of math progress in eight weeks. I asked the DeepMind researcher behind the trial ...
IEEE

Efficient Communication via Self-Supervised Information Aggregation for Online and Offline Multiagent Reinforcement Learning

Abstract: Utilizing messages from teammates can improve coordination in cooperative multiagent reinforcement learning (MARL). Previous works typically combine raw messages of teammates with local ...