Prior art research: https://github.com/cirosantilli/awesome-reinforcement-learning-games
The goal of this project is to reach artificial general intelligence.
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". For example:
- when you press a button here, a door opens somewhere far away
- when you touch certain types of objects, a chemical reaction may happen, but not other types of objects
Much in the spirit of gvgai, we have to do the following loop:
- create an initial game that a human can solve
- find an AI that beats it well
- study the AI, and add a new mechanic that breaks the AI, but does not break a human!
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 with more historical context, page 35:
There may, however, be a residual cultural effect on the AI community of its earlier history that makes many mainstream researchers reluctant to align themselves with over-grand ambition. Thus Nils Nilsson, one of the old-timers in the field, complains that his present-day colleagues lack the boldness of spirit that propelled the pioneers of his own generation:Concern for "respectability" has had, I think, a stultifying effect on some AI researchers. I hear them saying things like, "AI used to be criticized for its flossiness. Now that we have made solid progress, let us not risk losing our respectability." One result of this conservatism has been increased concentration on "weak AI" - the variety devoted to providing aids to human thought - and away from "strong AI" - the variety that attempts to mechanize human-level intelligenceNilsson’s sentiment has been echoed by several others of the founders, including Marvin Minsky, John McCarthy, and Patrick Winston.
- https://github.com/deepmind/lab2d: 2D gridworld games, C++ with Lua bindings
- https://www.youtube.com/watch?v=MHFrhIAj0ME?t=4183 Can't get you out of my head by Adam Curtis (2021) Part 1: Bloodshed on Wolf Mountain :)
- https://www.youtube.com/watch?v=EUjc1WuyPT8 AI alignment: Why It's Hard, and Where to Start by Eliezer Yudkowsky (2016)
- https://agents.inf.ed.ac.uk/blog/multiagent-learning-environments/ Multi-Agent Learning Environments (2021) by Lukas Schäfer from the Autonomous agents research group of the University of Edinburgh. One of their games actually uses apples as visual represntation of rewards, exactly like Ciro's game. So funny. They also have a 2d continuous game: https://agents.inf.ed.ac.uk/blog/multiagent-learning-environments/#mpe
- AI training game
- Artificial general intelligence
- Can AGI be trained in simulations?
- Human brain
- Machine learning
- Questions for Ciro Santilli's future self
- Real-time attack speedrun
- Universal basic income
- When the École Polytechnique mathematics department didn't let Ciro Santilli do his internship of choice due to grades