Ciro Santilli @cirosantilli 37

Prototype: github.com/cirosantilli/Urho3D-cheat

Prior art research: github.com/cirosantilli/awesome-reinforcement-learning-games

Less good discrete prototype: github.com/cirosantilli/rl-game-2d-grid YouTube demo: Video 1. "Top Down 2D Continuous Game with Urho3D C++ SDL and Box2D for Reinforcement learning by Ciro Santilli (2018)".

The goal of this project is to reach artificial general intelligence.

A few initiatives have created reasonable sets of robotics-like games for the purposes of AI development, most notably: OpenAI and DeepMind.

However, all projects so far have only created sets of unrelated games, or worse: focused on closed games designed for humans!

What is really needed is to create a single cohesive game world, designed specifically for this purpose, and with a very large number of game mechanics.

Notably, by "game mechanic" is meant "a magic aspect of the game world, which cannot be explained by object's location and inertia alone" in order to test the the missing link between continuous and discrete AI.

Much in the spirit of gvgai, we have to do the following loop:

The question then becomes: do we have enough computational power to simulation a game worlds that is analogous enough to the real world, so that our AI algorithms will also apply to the real world?

To reduce computation requirements, it is better to focus on a 2D world at first. Such world with the right mechanics can break any AI, while still being faster to simulate than a 3D world.

The initial prototype uses the Urho3D open source game engine, and that is a reasonable project, but a raw Simple DirectMedia Layer + Box2D + OpenGL solution from scratch would be faster to develop for this use case, since Urho3D has a lot of human-gaming features that are not needed, and because 2019 Urho3D lead developers disagree with the China censored keyword attack.

Simulations such as these can be viewed as a form of synthetic data generation procedure, where the goal is to use computer worlds to reduce the costs of experiments and to improve reproducibility.

Ciro has always had a feeling that AI research in the 2020's is too unambitious. How many teams are actually aiming for AGI? When he then read Superintelligence by Nick Bostrom (2014) it said the same. AGI research has become a taboo in the early 21st century.

Related projects:

Related ideas:

Bibliograpy:

The main ones as of 2020 are:

Maybe Ciro Santilli should do something useful and remarkable so that someone might actually want to read his biography in the first place. But hey, procrastination.

Ciro Santilli was born in Brazil in the small/medium city of Rio Claro, São Paulo (~200k people in 2020) in the State of São Paulo in 1989 AD.

The family then moved to Jundiaí in 1995, and then finally to Santos, São Paulo, Brazil in 1997.

At the age of 10, Ciro Santilli spent 10 months in Coventry, United Kingdom, where he greatly improved his English.

After Coventry, Ciro's family went back to Santos, São Paulo, Brazil, which made a deep impression on Ciro, until he Ciro Santilli's undergrad studies at the University of São Paulo in 2007.

In 2010, as mentioned at Section "Ciro Santilli's formal education", Ciro as admitted in a double degree program at the École Polytechnique, France, where he stayed until 2013. Going to France was a mind blowing, life changing event.

Ciro Santilli never did any illegal drugs, because he:so don't expect any amazing stories here.

Like LDS believers, Ciro never drinks coffee nor smokes, and only drinks alcohol and tea sparingly, because they are all addictive drugs and bring no net increase of energy and concentration.

Ciro prefers to only enjoy a glass of tea when going out cycling on a cold day (Earl gray, with milk, no sugar), or get a half pint of beer when going out with friends to a pub.

Ciro only got reasonably drunk twice on his life:

Later in life, around the time of his wedding, there were guests around all the time, and he was drinking beer with them all the time. Then one day, during lunch, Ciro felt a weirdly strong desire to drink one more pint. It was at this point that Ciro realized first-hand what mild, but real, alcohol addiction felt like, and he didn't get that drink, and swore from then on to never drink more than one glass a week, and only with friends at a bar after work. Richard Feynman tells a very similar story on his book Surely You're Joking, Mr. Feynman chapter O Americano, Outra Vez!, see: Section "Richard Feynman's drug use".

It would be amazing to answer this with single particle double slit experiment measurements!

Sequencing the DNA tells us what the organism can do. Sequencing the RNA tells us what the organism is actually doing at a given point in time. The problem is not killing the cell while doing that. Is it possible to just take a chunk of the cell to sequence without killing it maybe?

The general result from eigendecomposition of a matrix:becomes:where $O$ is an orthogonal matrix, and therefore has $O^{-1}=O^T$.