Month: December 2019
Deep double descent
We show that theĀ doubleĀ descentĀ phenomenonĀ occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with increasing model size, data size, or...
Weiterlesen
Procgen Benchmark
Weāre releasing Procgen Benchmark, 16 simple-to-useĀ procedurally-generatedĀ environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizableĀ skills.
Weiterlesen