10 PM CET = 01 PM PT

AI meets videogames

We created a place where to watch artificial intelligence algorithms grow and learn,
combat one versus the other, and fight against humans.

Live matches, tournaments, technical discussions, coding sessions, and much more.


Clips extracted from our Twitch lives as well as additional videos also focusing on related topics, like Reinforcement Learning implementation details, fun facts, behind the scenes content and much more.


Live streams and collection of all past episodes showing A.I. algorithms in action, competing in every game and in every mode, coding sessions and technical discussions about the amazing AI world.


Stories and cool pictures showing perspectives and shedding light on this fun field.

Join our Discord server

Discord Server


Sign up to receive all our updates!


Dead or Alive ++

Street Fighter III

Tekken Tag Tournament

Ultimate Mortal Kombat

Dreaming about seeing other games? Wishing to watch other game modes? Let us know, request a feature here!.



The Super Classic: live game sessions where A.I. algorithms, trained to beat the good old COM opponent, aim at completing the game and obtaining maximum score.

To take part in the "VS COM" competition, register your agent here.

A.I. VS A.I.

DIAMBRA Tournament: its name is "A.I. Battle". Best A.I. algorithms will fight their way through qualifying rounds and direct elimination matches to win the Title and become champions.

To take part in the "A.I. Battle" tournament, register your agent here.

A.I. VS Human

The Ultimate Fight: Who will get the upper hand in this endless match? Will current state-of-the-art A.I. algorithms be able to achieve super-human performances?


To leave a feedback about what we do,
complete this survey.

To contact us, use the form below.



Creator / Chief Technology Alchemist

Dreams, Vision & Passion
All Tech Stuff (Multiple Full Stacker):
DeepLearning, Reinforcement Learning,
Python Dev, MultiThreading, Input Devices Interface,
Gaming, Testing, Debugging,
Graphics, Branding, Socials, ...


Gaming / Testing

Platform Testing
Player Experience Collection
A.I. Algorithms Challenger

Pedro Pistolas

Gaming / Testing

Platform Testing
Player Experience Collection
A.I. Algorithms Challenger

Lord Morgul

Gaming / Testing

Platform Testing
Player Experience Collection
A.I. Algorithms Challenger

Collaborations available | Contribute

Deep Learning / Reinforcement Learning
Computer Vision / Embedded Devices
Graphics / Image & Video Editing
Social Media / Branding


Imitation learning

Imitation learning is a technique that, given a collection of examples (usually provided by humans) representing a "desirable behavior" in solving a specific task, uses it to train an agent, with the aim of making it learn how to achieve the same human-level performances. It can be used, for example, as a starting point to speed-up training, providing a reference baseline from where the agent can start experimenting and exploring. With the aim of demonstrating as many interesting RL techniques as possible, we equipped DIAMBRA with Imitation Learning capabilities, we will show and walk you through them during our live events.


While developing DIAMBRA, we wanted to make available most advanced and interesting Reinforcement Learning techniques, and self-play is for sure one of them. The platform allows the agent to play on both sides at the same time, being the challenger of himself. This technique is known to improve training, in particular because the agent will continuously face an opponent of the same ability level and also because for a single environment step it collects twice as much information.

The story behind DIAMBRA name

Naples, 1552. Two women, Isabella of Carazzi and DIAMBRA of Pottinella, in the presence of the Marquis of the Vast, dispute in a duel for the love of a man called Fabio Zeresola. This legendary episode, subject matter of the painting "Women Gladiators", by Jusepe de Ribera, Naples 1636, has also been held to be an allegory of the fight between Vice and Virtue.