https://github.com/mongark/superagent
Hobby project to create an Artificial General Intelligence in Rust.
https://github.com/mongark/superagent
artificial-general-intelligence artificial-intelligence rust-language
Last synced: 2 months ago
JSON representation
Hobby project to create an Artificial General Intelligence in Rust.
- Host: GitHub
- URL: https://github.com/mongark/superagent
- Owner: Mongark
- Created: 2022-11-26T21:46:33.000Z (over 3 years ago)
- Default Branch: main
- Last Pushed: 2022-12-30T16:48:00.000Z (over 3 years ago)
- Last Synced: 2025-01-19T22:51:05.741Z (over 1 year ago)
- Topics: artificial-general-intelligence, artificial-intelligence, rust-language
- Language: Rust
- Homepage:
- Size: 10.7 KB
- Stars: 0
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: docs/README.md
Awesome Lists containing this project
README
# Super Agent Documentation
## Introduction
A *Super Agent* is an intelligent system capable of self-sustaining growth and learning on a complex environment. It can learn new skills based on need, interest, and projections. Most of its behaviours should emerge from a set of basic components, so that the generalist principles that brought it forth can be latter be modified by the same.
This *Super Agent* is not only intended to be able to learn and grow, but to be a self-reliable emotional being capable of feeling a broad range of emotions including, but not limited to, "human emotions".
## Architecture
### The Scheduler
It becomes evident that a complex agent spanning multiple processing nodes would require some form of event based scheduler. An event cycle is a set of steps the Scheduler goes through to complete an arbitrary task.
### Tasks
Tasks are a piece of code that must be run on the Scheduler.
### Events
Stateful units capable of performing a unit of computation.
There are two state pipelines:
- `Execution` COLD, WARMING, RUNNING, STOPPING, STOPPED.
- `Termination` TERMINATING, TERMINATED
## General Definitions
### Artificial Intelligence
*Artificial Intellifece*, or *AI*, is the field that studies the synthesis and analysis of computational agents that act intelligently.
### Agents
An *Agent* is something that acts in an environment. An Agent acts intelligently when:
* what it does is appropriate for its circumstances and its goals, taking into account the short-term and long-term consequences of its actions
* it is flexible to changing environments and changing goals
* it learns from experience
* it makes appropriate choices given its perceptual and computational limitations
### Emergent Algotithms
An *emergent algorithm* is an algorithm that exhibits emergent behavior. In essence an emergent algorithm implements a set of simple building block behaviors that when combined exhibit more complex behaviors.
### Emergence
In philosophy, systems theory, science, and art, *emergence* occurs when an entity is observed to have properties its parts do not have on their own, properties or behaviors that emerge only when the parts interact in a wider whole.
## Personal Definitons
### Purely Algorithmic Perspective
When one sees an algorithm in relation to how it affects data, rather than its more specific application. It generalizes an algorithm such that it can be applied on other use cases.
## Todo
### Events Scheduler
### Actuator Interface
### Sensor Interface
### Emergent Emotional Engine
-[ ] Search for arxiv papers on "Emergent Emotional Behaviour"
### Memory Engine
-[ ] Search current methods of emulating AI memory
-[ ] Memory Management System
### To-Read
* [Abstraction](https://en.wikipedia.org/wiki/Abstraction)
* [Agent-based model](https://en.wikipedia.org/wiki/Agent-based_model)
* [Connectionism](https://en.wikipedia.org/wiki/Connectionism)
* [Dual-phase evolution](https://en.wikipedia.org/wiki/Dual-phase_evolution)
* [Emergent gameplay](https://en.wikipedia.org/wiki/Emergent_gameplay)
* [Generative science](https://en.wikipedia.org/wiki/Generative_science)
* [Irreducible complexity](https://en.wikipedia.org/wiki/Irreducible_complexity)
* [Langton's ant](https://en.wikipedia.org/wiki/Langton%27s_ant)
* [Neural Network](https://en.wikipedia.org/wiki/Neural_network)
* [Polytely](https://en.wikipedia.org/wiki/Polytely)
* [Supervenience](https://en.wikipedia.org/wiki/Supervenience)
* [Swarm intelligence](https://en.wikipedia.org/wiki/Swarm_intelligence)
* [System of systems](https://en.wikipedia.org/wiki/System_of_systems)
* [Spontaneous order](https://en.wikipedia.org/wiki/Spontaneous_order)
* [Synergetics(Fuller)](https://en.wikipedia.org/wiki/Synergetics_(Fuller))
* [Synergetics(Haken)](https://en.wikipedia.org/wiki/Synergetics_(Haken))
* [Category: Pattern formation](https://en.wikipedia.org/wiki/Category:Pattern_formation)