Posted by Sneha Kudugunta, Research Software Engineer and Orhan Firat, Research Scientist, Google Research Scaling large language models has resulted in significant quality improvements natural language understanding (T5), generation (GPT-3)… Read More »Learning to Route by Task for Efficient Inference
When humans look at a scene, they see objects and the relationships between them. On top of your desk, there might be a laptop that is sitting to the left… Read More »Artificial intelligence that understands object relationships
Explore the Common Grounds experience from your desktop Visit Common Grounds Download the app for your mobile device Visitors from around the world flock to Ancient Olympia to get a… Read More »Digitally preserving and restoring Ancient Olympia as it stood over 2,000 years ago
Posted by Florian Hartmann, Software Engineer, Google Research Smart Text Selection, launched in 2017 as part of Android O, is one of Android’s most frequently used features, helping users select,… Read More »Predicting Text Selections with Federated Learning
When the cloud storage firm Dropbox decided to shut down its offices with the outbreak of the Covid-19 pandemic, co-founder and CEO Drew Houston ’05 had to send the company’s nearly… Read More »In MIT visit, Dropbox CEO Drew Houston ’05 explores the accelerated shift to distributed work
Sequence Modeling Solutions for Reinforcement Learning Problems
Long-horizon predictions of (top) the Trajectory Transformer compared to those of (bottom) a single-step dynamics model.
Modern machine learning success stories often have one thing in common: they use methods that scale gracefully with ever-increasing amounts of data. This is particularly clear from recent advances in sequence modeling, where simply increasing the size of a stable architecture and its training set leads to qualitatively different capabilities.
Meanwhile, the situation in reinforcement learning has proven more complicated. While it has been possible to apply reinforcement learning algorithms to large–scale problems, generally there has been much more friction in doing so. In this post, we explore whether we can alleviate these difficulties by tackling the reinforcement learning problem with the toolbox of sequence modeling. The end result is a generative model of trajectories that looks like a large language model and a planning algorithm that looks like beam search. Code for the approach can be found here.
Posted by David Ha, Staff Research Scientist and Yujin Tang, Research Software Engineer, Google Research, Tokyo “The brain is able to use information coming from the skin as if it… Read More »Permutation-Invariant Neural Networks for Reinforcement Learning