189 citations · 505 across the 15 of their papers we have counts for
4 papers · 1 filter
WebGPT: Browser-assisted question-answering with human feedback
Reiichiro Nakano, Jacob Hilton, Suchir Balaji +15
We fine-tune GPT-3 to answer long-form questions using a text-based web-browsing environment, which allows the model to search and navigate the web. By setting up the task so that…
Training Verifiers to Solve Math Word Problems
Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian +9
State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning. To diagnose the failures…
Batch size-invariance for policy optimization
Jacob Hilton, Karl Cobbe, John Schulman
We say an algorithm is batch size-invariant if changes to the batch size can largely be compensated for by changes to other hyperparameters. Stochastic gradient descent is well-kno…
Measuring Sample Efficiency and Generalization in Reinforcement Learning Benchmarks: NeurIPS 2020 Procgen Benchmark
Sharada Mohanty, Jyotish Poonganam, Adrien Gaidon +20
The NeurIPS 2020 Procgen Competition was designed as a centralized benchmark with clearly defined tasks for measuring Sample Efficiency and Generalization in Reinforcement Learning…