no code implementations • 13 Feb 2024 • Aaron Traylor, Jack Merullo, Michael J. Frank, Ellie Pavlick
Models based on the Transformer neural network architecture have seen success on a wide variety of tasks that appear to require complex "cognitive branching" -- or the ability to maintain pursuit of one goal while accomplishing others.
no code implementations • 13 Feb 2024 • Jacob Russin, Ellie Pavlick, Michael J. Frank
Human learning is sensitive to rule-like structure and the curriculum of examples used for training.
no code implementations • 7 Nov 2022 • Lucas Lehnert, Michael J. Frank, Michael L. Littman
Recent advances in reinforcement-learning research have demonstrated impressive results in building algorithms that can out-perform humans in complex tasks.