Generalizing from simulation

OpenAI Blog2017-10-19 15:000 views

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

Source：https://openai.com/index/generalizing-from-simulation

My favorites

PreviousLearning a hierarchy NextSim-to-real transfer of robotic control with dynamics randomization

How Long Does It Take to Learn Programming?

One of the first questions almost every aspiring programmer asks is: " How long will it take me to learn programming? "

0dev.to Programming

Code Reviews y Desarrollo Full Stack: Cómo Estructurar el Aprendizaje Técnico en la Era de la IA

La disponibilidad de asistentes de generación de código ha cambiado la velocidad con la que se escriben funciones, pero

0dev.to Programming

Building an Async Java REST Client with CompletableFuture, Concurrent Requests, and Virtual Threads

Synchronous HTTP code is simple. But sometimes your application needs to call several APIs at once, reduce waiting time,

0dev.to Java

Marketplace Page Alerts: Debug Duplicate Chunks Across Vector Results

TL;DR: Give every marketplace page snapshot a stable version, derive each chunk ID from that version plus its position,

0dev.to TypeScript

5,100 draw calls to 270: 3D building instructions for a 1,689-part brick model on a phone

We build BrickPlay : step-by-step 3D building instructions that open in the browser from a QR code on the box. No app, t

0dev.to JavaScript

Why a soft shadow prints as white dots: checking customer images before UV printing

At Kloniko customers upload their own images to print on a figure: a face, a logo on a torso, a pattern on the legs. In