John Conway's Game of Life

Life Is Easier for Big Networks

According to the lottery ticket hypothesis, the bigger the neural network, the more likely some of its weights are initialized to values that are well suited to learning to perform the task at hand. But just how big does it need to be?
Takes from Agence, an interactive VR project

RL Agents: SOS!

A new multimedia experience lets audience members help artificially intelligent creatures work together to survive. Agence, an interactive virtual reality (VR) project blends audience participation with reinforcement learning to create an experience that’s half film, half video game.
Map of the area analyzed in Cascadia and sketch of the subduction zone

Prelude to a Quake?

Geologists call them slow slips: deep, low-frequency earthquakes that can last a month but have little effect on the surface. A model trained to predict such events could help with forecasting potentially catastrophic quakes.
Different chess moves

Chess: The Next Move

AI has humbled human chess masters. Now it’s helping them take the game to the next level. DeepMind and retired chess champion Vladimir Kramnik trained AlphaZero, a reinforcement learning model that bested human experts in chess, Go, and Shogi, to play-test changes in the rules.
Tennis simulator Vid2Player working

Wimbledon in a Box

Covid shut down the tennis tournament at Wimbledon this year, but a new model simulates showdowns between the sport’s greatest players. Stanford researchers developed Vid2Player, a system that simulates the footwork, positioning, and strokes of tennis pros like Roger Federer.
Sequence of an autonomous fighter pilot

AI Versus Ace

An autonomous fighter pilot shot down a human aerial ace in virtual combat. Built by defense contractor Heron Systems, the system also defeated automated rivals from seven other companies to win the AlphaDogfight trial.
Dozens of drones coordinating movements

Drones of a Feather

Deep learning is coordinating drones so they can flock together without colliding. Caltech researchers Soon-Jo Chung and Yisong Yue developed a pair of models that enables swarms of networked drones to navigate autonomously through cluttered environments.
Information related to Policy Adaptation during Deployment (Pad)

Same Job, Different Scenery

People who take driving lessons during daytime don’t need instruction in driving at night. They recognize that the difference doesn’t disturb their knowledge of how to drive. Similarly, a new reinforcement learning method manages superficial variations in the environment without re-training.
Data related to a new reinforcement learning approach

Eyes on the Prize

When the chips are down, humans can track critical details without being distracted by irrelevancies. New research helps reinforcement learning models similarly focus on the most important details.
Takes from videogame Source of Madness

Monsters in Motion

How do you control a video game that generates a host of unique monsters for every match? With machine learning, naturally. The otherworldly creatures in Source of Madness learn how to target players through reinforcement learning.
Graphs and data related to Plan2Vec

Visual Strategies for RL

Reinforcement learning can beat humans at video games, but humans are better at coming up with strategies to master more complex tasks. New work enables neural networks to connect the dots.
Results of a technique that interprets reflected light to reveal objects outside the line of sight

Periscope Vision

Wouldn’t it be great to see around corners? Deep learning researchers are working on it. Researchers developed deep-inverse correlography, a technique that interprets reflected light to reveal objects outside the line of sight.
Anima Anandkumar

Anima Anandkumar: The Power of Simulation

We’ve had great success with supervised deep learning on labeled data. Now it’s time to explore other ways to learn: training on unlabeled data, lifelong learning, and especially letting models explore a simulated environment before transferring what they learn to the real world.
Illustration of a crystal snowball

Simulation Substitutes for Data

The future of machine learning may depend less on amassing ground-truth data than simulating the environment in which a model will operate. Deep learning works like magic with enough high-quality data. When examples are scarce, though, researchers are using simulation to fill the gap.
Information related to Implicit Reinforcement without Interaction at Scale (IRIS)

Different Skills From Different Demos

Reinforcement learning trains models by trial and error. In batch reinforcement learning (BRL), models learn by observing many demonstrations by a variety of actors. But what if one doctor is handier with a scalpel while another excels at suturing?

Subscribe to The Batch

Stay updated with weekly AI News and Insights delivered to your inbox