Skip to main content

Facebook’s AI Started Speaking Its Own Language And Negotiating Like Humans


Facebook-ai
Researchers at Facebook trained their AI bot which they call ‘dialog agent’ to negotiate like humans and even converse in natural English language to the extent that even people find it hard to know if they are talking to an AI. They have open sourced the dataset and
code of their machine learning algorithm.
The AI chatbots can do a lot of things for us. They can tell us a joke, book a table, or take slangs we throw at them as if they’re unaware of it. But the researchers at FAIR (Facebook Artificial Intelligence Research) think the AI can do far more than just ordering groceries; they can create their own language and even negotiate with people.
New research published by FAIR describes how the bots, referred as ‘dialog agents’ were trained to develop the ability to negotiate. Through the training process which involved machine learning algorithms and intelligence strategies, agents were able to bargain against each other for the things they liked more.
The agents developed the ability to negotiate for a long time without giving up, use tactics which weren’t programmed by the researchers, and produce more natural language.
facebook ai negotiation
Image: Facebook Research
Much to the surprise of the researchers, the dialog agents started negotiating in an entirely new language when they were left to converse without human attention. However, the researchers prevented this situation, making one of agent give responses in the English language as a human would do.
The supervised pre-training involved feeding an agent with a set of negotiations crowdsourced from people, and agents were able to imitate humans in situations. Later, the researchers used reinforcement learning so that the agents could learn thousands of negotiations on its own and get rewarded.
Supervised learning was used to teach how to map between language and meaning. On the other hand, reinforcement learning helped the agent with what to say and when.
When placed in front of humans (online) who didn’t know who they were chatting with, an agent matched negotiation skills of humans along with English as fluent that the people were left unsuspecting about its existence.
The new algorithm can help developers create advanced bots that reason, converse, and negotiate better, the researchers said in their blog post. These are all vitals to making a personalized digital assistant, and maybe, we could even see AI brokers getting cheap home deals for us.
You can find more details about the research titled ‘Deal or no deal? Training AI to negotiate’ using this link. Its open source code is now available on Github.
Got something to add? Drop your thoughts and feedback inside comments.

Comments

Follow Us

WHAT'S HOT

VIDEO: KLY & DJ Maphorisa ft. eMTee & Patoranking – SnapThatSh!t

Ambitiouz Entertainment presents the official music video to “SnapThatSh!t” by its budding act, KLYalongside prolific South African producer, Maphorisa, raving South African rapper, eMTee and Nigeria’s music sensation, Patoranking.

How To Install Ubuntu MATE For The Raspberry Pi 2 and Raspberry Pi 3

Ubuntu MATE:  We have done what we can to optimise the build for the Raspberry Pi 2 and Raspberry Pi 3, you can comfortably use applications such as LibreOffice and Firefox. But the microSDHC I/O throughput is a bottleneck so  we  highly  recommend that you use a Class 6 or Class 10 microSDHC  card.  Ubuntu MATE 16.04 also fully supports the built-in Bluetooth and Wifi on

Windows Subsystem For Linux Is Beta No More, Gets “Full Support” In Windows 10 Fall Creators Update

As we told you earlier, WSL on Windows 10  moved out of beta  in August. It still carries the beta tag in Windows 10 Creators Update. Also, it won’t require people to enable developer

KLY Ft. Wizkid – Scrrr Pull Up (Remix)

Starboy, Wizkid blends with KLY as he adds a verse to Kly’s hottest tune Pull up Scrr!!. The remix comes with heavy greatness verse from the starboy boss as he blended another magic lyrics on the self enriched tune. Song Production credit goes to Wichi 1080.