Reinforcement Learning

Both transformers and reinforcement learning models are notoriously data-hungry. They may be less so when they work together. Vincent Micheli and colleagues at the University of Geneva trained a transformer-based system to simulate Atari games using a small amount of gameplay.

Roboticists often train their machines in simulation, where the controller model can learn from millions of hours of experience. A new method trained robots in the real world in 20 minutes.

Autonomous robots trained to navigate in a simulation often struggle in the real world. New work helps bridge the gap in a counterintuitive way.

Reinforcement learning is powering a new generation of video game cheaters. Players of Rocket League, a video game that ranks among the world’s most popular esports, are getting trounced by cheaters who use AI models originally developed to train contestants.

Amid speculation about the threat posed by OpenAI’s ChatGPT chatbot to Google’s search business, a paper shows how the search giant might address the tendency of such models to produce offensive, incoherent, or untruthful dialog.

Recent advances in deep learning largely have come by brute force: taking the latest architectures and scaling up compute power, data, and engineering. Do we have the architectures we need, and all that remains is to develop better hardware and datasets so we can keep...

A new algorithm defeated a championship-winning Go model using moves that even a middling human player could counter. Researchers trained a model to defeat KataGo, an open source Go-playing system that has beaten top human players.

A new method enables robots to respond helpfully to verbal commands by pairing a natural language model with a repertoire of existing skills.

Robots trained via reinforcement learning usually study videos of robots performing the task at hand. A new approach used videos of humans to pre-train robotic arms.

A dog doesn’t think twice about fetching a tennis ball, but an autonomous robot typically suffers from delays between perception and action. A new machine-learning model helped a quadruped robot coordinate its sensors and actuators.

Nuclear fusion technology, long touted as an unlimited source of safe, clean energy, took a step toward reality with a machine learning algorithm that molds the fuel in a reactor’s core.

Armchair speed demons have a new nemesis. Peter Wurman and a team at Sony developed Gran Turismo Sophy (GT Sophy), a reinforcement learning model that defeated human champions of Gran Turismo Sport, a PlayStation game that simulates auto races right down to tire friction and air resistance.

Nothing is certain except death and taxes, the saying goes — but how to make taxes fair and beneficial remains an open question. New research aims to answer it.

Robots are tremendously useful machines, and I would like to see them applied to every task where they can do some good. Yet we don’t have enough programmers for all this hardware and all these tasks.

Transformers have matched or exceeded earlier architectures in language modeling and image classification. New work shows they can achieve state-of-the-art results in some reinforcement learning tasks as well.