Zephyrnet Logo

Tag: agents

Specifying AI safety problems in simple environments

In this gridworld, the agent must navigate a ‘warehouse’ to reach the green goal tile via one of two routes. It can head...

How high-growth companies are scaling customer service across multiple languages

Exactly how do companies like Skyscanner, Daniel Wellington, Pinterest and Under Armour scale their customer service operations across multiple languages?Do they hire hundreds...

How to transform customer support for business excellence

Customer Support often has a bad name. And that’s strange. Because everyone who works in customer service also knows exactly what it’s like...

Daniel Wellington, Europe’s fastest growing company, uses Unbabel to support its global customer community

Daniel Wellington is a watch brand, known for sleek and timeless design, its interchangeable NATO straps and mid-price positioning. Founded in Stockholm, Sweden...

Introducing Unbabel Translate for Freshdesk

A new way to deliver multilingual customer supportOver 100,000 companies trust Freshworks to deliver great software experiences in their day to day business,...

How Artificial Intelligence is changing the SaaS Landscape

There is no one moment when SaaS – Software as a Service – was conceived, because SaaS as a concept has a host...

DeepMind and Blizzard open StarCraft II as an AI research environment

StarCraft and StarCraft II are among the biggest and most successful games of all time, with players competing in tournaments for more than...

DeepMind papers at ICML 2017 (part two)

DARLA: Improving Zero-Shot Transfer in Reinforcement LearningAuthors: Irina Higgins*, Arka Pal*, Andrei Rusu, Loic Matthey, Chris Burgess, Alexander Pritzel, Matt Botvinick, Charles Blundell,...

AI and Neuroscience: A virtuous circle

Another key challenge in contemporary AI research is known as transfer learning. To be able to deal effectively with novel situations, artificial agents...

How Artificial Intelligence is changing the gaming industry

Artificial intelligence (AI) in gaming isn’t a recent innovation. As early as 1949, mathematician and cryptographer Claude Shannon pondered a one-player chess game, in...

Agents that imagine and plan

Testing our architecturesWe tested our proposed architectures on multiple tasks, including the puzzle game Sokoban and a spaceship navigation game. Both games require...

Learning through human feedback

In the Atari game Enduro, which involves steering a car to overtake a line of others and is very difficult to learn by...

Latest Intelligence

spot_img
spot_img