https://github.com/h-iaac/cst-rl
https://github.com/h-iaac/cst-rl
Last synced: 3 months ago
JSON representation
- Host: GitHub
- URL: https://github.com/h-iaac/cst-rl
- Owner: H-IAAC
- Created: 2023-04-24T18:37:32.000Z (about 2 years ago)
- Default Branch: main
- Last Pushed: 2024-05-22T17:31:55.000Z (about 1 year ago)
- Last Synced: 2024-05-22T18:43:08.629Z (about 1 year ago)
- Language: Python
- Size: 6.67 MB
- Stars: 0
- Watchers: 9
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
CST-RL is a framework for building assynchronous RL agents as part of a larger cognitive architecture through the [Cognitive Systems Toolkit (CST)](https://cst.fee.unicamp.br/). Its focus is largely on solving the structural and communication challenges of an assynchrounous RL agent rather than the specifics of the algorithms implemented. As such, while a couple of benchmark algorithms are implemented directly in Java, the plan is to implement more state-of-the-art algorithms through the use of external libraries.
Moreover, this repository uses the open-source game engine [Godot](https://godotengine.org/) to build complex environments through the use of the [CST-Godot framework](https://godotengine.org/).
This repository is divided in the following sections
- [Python](#python)
- [Godot](#godot)
- [CST-RL](#cst-rl)
# Python
Includes a simple Python script that uses [NumPy](https://numpy.org/) and [Pyplot](https://matplotlib.org/stable/tutorials/introductory/pyplot.html) to generate graphs from CSV files. This is used to generate graphs of cummulative reward over time of different algorithms from the CSV files generated by CST-RL.
# Godot
The Godot project used as environment for the RL algorithm. It communicates with CST through the use of HTTP requests.
# CST-RL
The framework itself. Here, it runs as a web API that communicates with a Godot environment, receiving percepts and returning actions.