Jul 07, 2021

6 Posts

Automated player learning by watching recorded gameplay
Jul 07, 2021

Behavioral Cloning Shootout

Neural networks have learned to play video games like Dota 2 via reinforcement learning by playing for the equivalent of thousands of years (compressed into far less time). In new work, an automated player learned not by playing for millennia but by watching a few days’ worth of recorded gameplay.
Cartoon about traditional software and AI
Jul 07, 2021

The Batch: Zillow's New Neural Net, Optimizing Traffic City-Wide, Classifying Creepy Crawlies, Behavioral Cloning

In a recent letter, I noted that one difference between building traditional software and AI products is the problem of complex product specification. With traditional software, product managers can specify a product in ways...
Video showing traffic signals controlled by AI
Jul 07, 2021

Lighter Traffic Ahead

Traffic signals controlled by AI are keeping vehicles rolling citywide. Several U.S. cities are testing systems from Israel-based startup NoTraffic that promise to cut both commute times and carbon emissions.
New approach to automated real-estate assessment
Jul 07, 2021

Home Sweet AI-Appraised Home

Real estate websites helped turn automated real-estate assessment into a classic AI problem. The latest approach by a leader in the field gets a boost from deep learning.
Series of imagen showing how an insect-sorting robot works
Jul 07, 2021

Bugbot

An insect-sorting robot could help scientists grapple with the global biodiversity crisis. An automated insect classifier sucks in tiny arthropods, classifies them, and maps their most important identifying features.
Cartoon about traditional software and AI
Jul 07, 2021

Developing AI Products Part 3: Coping With Product Specification

In a recent letter, I noted that one difference between building traditional software and AI products is the problem of complex product specification.

Subscribe to The Batch

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