Data

Tools

Indexes

Applications

Experiments

Open Source Science

decaf

Framework for training, curating and explaining agents behaviors' at general problems.

https://github.com/louie-jones-strong/decaf

Science Score: 44.0%

This score indicates how likely this project is to be science-related based on various indicators:

  • ✓
    CITATION.cff file
    Found CITATION.cff file
  • ✓
    codemeta.json file
    Found codemeta.json file
  • ✓
    .zenodo.json file
    Found .zenodo.json file
  • ○
    DOI references
  • ○
    Academic publication links
  • ○
    Academic email domains
  • ○
    Institutional organization owner
  • ○
    JOSS paper metadata
  • ○
    Scientific vocabulary similarity
    Low similarity (11.5%) to scientific vocabulary

Keywords

artificial-intelligence bachelor-degree dissertation-project machine-learning reinforcement-learning
Last synced: 6 months ago · JSON representation ·

Repository

Framework for training, curating and explaining agents behaviors' at general problems.

Basic Info
  • Host: GitHub
  • Owner: louie-jones-strong
  • License: mit
  • Language: Python
  • Default Branch: main
  • Homepage:
  • Size: 95.7 MB
Statistics
  • Stars: 0
  • Watchers: 1
  • Forks: 0
  • Open Issues: 3
  • Releases: 0
Topics
artificial-intelligence bachelor-degree dissertation-project machine-learning reinforcement-learning
Created over 3 years ago · Last pushed over 1 year ago
Metadata Files
Readme License Citation

README.md

Dynamic Exploration of Curated Agents Framework (DECAF)

Status

Unit Tests Lint Checks Docs Build <!-- Type Hint Checks -->

About

This project has been created as part of my final year dissertation at the University of London. The project is an implementation of the reinforcement learning framework DECAF, proposed in my dissertation. DECAF trains agents' policies to maximise the expected reward in a environment. DECAF allows for tuning the agents' behaviours to mimic human behaviours or a custom curated behaviour.

Find the documentation here

Requirements

Quick Start

  1. Clone the repository
  2. Run the following commands in the root directory Setup.bat docker-compose build docker-compose up
  3. Navigate to localhost:5000 in your browser

You can modify the settings in the .env file.

Logging to wandb

To log runs to wandb, create a file called secrets.env in the root directory with the following contents: WANDB_API_KEY=<your api key>

Local Development

Note. The trajectory server will not work on Windows.

  1. Run Setup.bat to create a virtual environment and install the required packages

Running Tests

Run RunTests.bat in the root directory to run all tests

Updating Documentation

Run CreateDocs.bat in the root directory to update the documentation

Owner

  • Name: Louie Jones-Strong
  • Login: louie-jones-strong
  • Kind: user
  • Location: Brighton, United Kingdom

Citation (CITATION.cff) 

cff-version: 1.2.0
message: "If you use this software, please cite it as below."
authors:
- family-names: "Jones-Strong"
  given-names: "Louie"
  orcid: "https://orcid.org/0009-0005-4629-9946"
title: "Dynamic Exploration of Curated Agents Framework"
version: 1.0.0
doi: 10.5281/zenodo.1234
date-released: 2023-09-07
url: "https://github.com/louie-jones-strong/DECAF"

GitHub Events

Total
Last Year

Dependencies

.github/workflows/DocsCreation.yml actions
  • actions/checkout v1 composite
  • actions/deploy-pages v2 composite
  • actions/upload-pages-artifact v2 composite
  • ammaraskar/sphinx-action master composite
.github/workflows/LintChecks.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
.github/workflows/TypeHintChecks.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
.github/workflows/UnitTests.yml actions
  • actions/checkout v3 composite
  • actions/setup-python v4 composite
src/ExperienceStore/Dockerfile docker
  • python 3.8.10 build
src/Learner/Dockerfile docker
  • tensorflow/tensorflow 2.12.0-gpu build
src/WebServer/Dockerfile docker
  • python 3.8.10 build
src/Worker/Dockerfile docker
  • tensorflow/tensorflow 2.12.0-gpu build
docs/requirements.txt pypi
  • flake8 ==6.0.0
  • mypy ==1.2.0
  • sphinx ==6.2.1
  • sphinx-autodoc-typehints ==1.23.0
  • sphinx-rtd-theme ==1.2.2
  • types-keyboard ==0.13.2.7
  • types-redis ==4.6.0.2
  • unittest-parallel ==1.5.3
requirements-dev.txt pypi
  • flake8 ==6.0.0 development
  • ipykernel * development
  • matplotlib * development
  • mypy ==1.2.0 development
  • pandas * development
  • pyperclip * development
  • seaborn * development
  • sphinx ==6.2.1 development
  • sphinx-autodoc-typehints ==1.23.0 development
  • sphinx-rtd-theme ==1.2.2 development
  • types-keyboard ==0.13.2.7 development
  • types-redis ==4.6.0.2 development
  • unittest-parallel ==1.5.3 development
setup.py pypi
src/ExperienceStore/requirements.txt pypi
  • dm-reverb ==0.11.0
  • gymnasium ==0.26.3
  • tensorboard ==2.12.0
  • tensorflow ==2.12.0
src/Learner/requirements.txt pypi
  • dm-reverb ==0.11.0
  • gymnasium ==0.26.3
  • keyboard ==0.13.5
  • numpy ==1.23.5
  • redis ==4.6.0
  • scikit-learn ==1.2.2
  • tensorboard ==2.12.0
  • tensorflow ==2.12.0
  • wandb ==0.15.2
  • xgboost ==1.7.5
src/WebServer/requirements.txt pypi
  • dm-reverb ==0.11.0
  • flask ==2.3.2
  • gymnasium ==0.26.3
  • numpy ==1.23.5
  • opencv-python-headless ==4.7.0.72
  • tensorflow ==2.12.0
src/Worker/requirements.txt pypi
  • dm-reverb ==0.11.0
  • gymnasium *
  • gymnasium ==0.26.3
  • keyboard ==0.13.5
  • numpy ==1.23.5
  • opencv-python-headless ==4.7.0.72
  • pygame ==2.4.0
  • redis ==4.6.0
  • scikit-learn ==1.2.2
  • tensorboard ==2.12.0
  • tensorflow ==2.12.0
  • wandb ==0.15.2
  • xgboost ==1.7.5