Retro Contest
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience. In typical RL research, algorithms are tested in the same environment where they were trained, which favors algorithms which are good at memorization and have many hyperparameters. Instead, our contest tests an
By Lance Eliot, the AI Trends Insider What do these aspects have in common: Roswell, Area 51, JFK assassination, moon landing, AI self-driving cars? They are all considered by some to be conspiracies. Most of us are familiar with Roswell, New Mexico and the claims of a UFO that landed there. Likewise, most of us […]