Deep double descent
We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with…
We show that the double descent phenomenon occurs in CNNs, ResNets, and transformers: performance first improves, then gets worse, and then improves again with…
We’re releasing Procgen Benchmark, 16 simple-to-use procedurally-generated environments which provide a direct measure of how quickly a reinforcement learning agent learns generalizable skills.
We’re releasing Safety Gym, a suite of environments and tools for measuring progress towards reinforcement learning agents that respect safety…
As the final model release of GPT-2’s staged release, we’re releasing the largest version (1.5B parameters) of GPT-2 along with code and model…
We’ve trained a pair of neural networks to solve the Rubik’s Cube with a human-like robot hand. The neural networks…
We are now accepting applications for our third class of OpenAI Scholars.
We’ve fine-tuned the 774M parameter GPT-2 language model using human feedback for various tasks, successfully matching the preferences of the…
We’ve observed agents discovering progressively more complex tool use while playing a simple game of hide-and-seek. Through training in our…
We’ve developed a method to assess whether a neural network classifier can reliably defend against adversarial attacks not seen during…