{"id":30860609,"url":"https://github.com/omarelfiki/unity-ml-drl-data","last_synced_at":"2026-05-07T04:41:25.685Z","repository":{"id":313014315,"uuid":"1049674728","full_name":"omarelfiki/unity-ml-drl-data","owner":"omarelfiki","description":"Collecting data on agents training/acting in 3D simulations and analyzing it with ML","archived":false,"fork":false,"pushed_at":"2025-09-03T12:21:58.000Z","size":5,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-03T12:27:51.459Z","etag":null,"topics":["3d-models","csharp","machine-learning","ml-agents","python","unity"],"latest_commit_sha":null,"homepage":"","language":"Mathematica","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/omarelfiki.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-03T10:28:35.000Z","updated_at":"2025-09-03T12:22:00.000Z","dependencies_parsed_at":"2025-09-03T12:27:53.134Z","dependency_job_id":"5a9b5845-0a30-42d0-9ac5-cd16064d651c","html_url":"https://github.com/omarelfiki/unity-ml-drl-data","commit_stats":null,"previous_names":["omarelfiki/unity-ml-drl-data"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/omarelfiki/unity-ml-drl-data","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omarelfiki%2Funity-ml-drl-data","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omarelfiki%2Funity-ml-drl-data/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omarelfiki%2Funity-ml-drl-data/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omarelfiki%2Funity-ml-drl-data/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/omarelfiki","download_url":"https://codeload.github.com/omarelfiki/unity-ml-drl-data/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/omarelfiki%2Funity-ml-drl-data/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":274059769,"owners_count":25215366,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-09-07T02:00:09.463Z","response_time":67,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["3d-models","csharp","machine-learning","ml-agents","python","unity"],"created_at":"2025-09-07T16:12:51.255Z","updated_at":"2026-05-07T04:41:25.673Z","avatar_url":"https://github.com/omarelfiki.png","language":"Mathematica","funding_links":[],"categories":[],"sub_categories":[],"readme":"# unity-ml-drl-data\n### Group 6 - P2-1: Artificial Intelligence \u0026 Machine Learning\nunity-ml-drl-data is a GitHub repository for experimenting with Deep Reinforcement Learning (DRL) using Unity and ML-Agents. \nThis project uses simulated 3D environments to study and train agents with DRL algorithms, while logging performance and behavioral data using TensorBoard for analysis using Machine Learning Techniques to make predictions on training results. \nMore information can be found in the [`docs/`](https://www.github.com/omarelfiki/unity-ml-drl-data/tree/main/docs) directory.\n\n### Repository Structure\n```\nunity-ml-drl-data/\n│\n├── unity/                 # Unity project files (scenes, agents, environment scripts)\n├── training/              # Python training scripts, configs, and utilities\n├── data/                  # Collected data and schema definitions\n├── docs/                  # Documentation, research notes, and reports\n├── models/                # Trained prediction models and ML evaluation scripts\n├── README.md              # This file\n├── CONTRIBUTING.md        # Guidelines for making contributions\n└── SETUP.md               # In-depth installation steps\n```\n\n### Installation\nClone Repository and setup Python Environment\n```\ngit clone https://github.com/omarelfiki/unity-ml-drl-data.git\ncd unity-ml-drl-data/training\npython setup_env.py\n```\n\u003e Unity 2023.2.12f1 is a requirement for this project. Unity versions can be downloaded via Unity Hub.\n\nSee [```SETUP.md```](https://www.github.com/omarelfiki/unity-ml-drl-data/tree/main/SETUP.md)for in-depth installation steps.\n\n### Training\nfrom ```training/```:\n```\npython -m scripts.train [-h] --config \u003cconfig_file\u003e --run-id \u003crun_id\u003e [--num-steps \u003cint\u003e] [--headless \u003cenv_path\u003e]\n```\n\u003e Example Usage for training script. Results will be appended to shared dataset. Local results are directed to gitignore.\n\nSee [```training/README.md```](https://www.github.com/omarelfiki/unity-ml-drl-data/tree/main/training/README.md) for more information on the `training` package.\n\n### Modeling\n\u003e See Models CLI on all collected environments and datasets through GitHub actions here: https://github.com/omarelfiki/unity-ml-drl-data/actions/workflows/run_models.yml. Artifacts can be downloaded. Contact repository administrators for run access.\n\nfrom ```models/```:\n```\npython -m scripts.run [-h] [--test_size \u003ctest_size\u003e] [--seed \u003cseed\u003e] [--thresh \u003cthresh\u003e] [--env \u003cenv\u003e] [--models-dir \u003cmodels_dir\u003e] [--data-csv, \u003cdata_csv\u003e]\n```\n\u003e Example Usage for modelling script. Results will be available under ```models/experiments/```\n\u003e \n\u003e Once completed, the results will be available in the artifacts tab of the workflow run as a zip file containing the collected models and results.\n\nSee [```models/README.md```](https://www.github.com/omarelfiki/unity-ml-drl-data/tree/main/modles/README.md) for more information on the `models` package.\n\n\n\n### Results\nResults are obtained in a shared dataset updated each training run with new metrics. Upon being pushed to the repository, data validation checks are executed automatically by GitHub workflows. A summary report is also available providing average dataset values and plots from TensorBoard data for visualization. \n\nSee [```data/```](https://www.github.com/omarelfiki/unity-ml-drl-data/tree/main/data) for results and documentation.\n\n\n## Attributions\nThis project includes the official **Unity ML-Agents Examples and corresponding training configuration files**, sourced from the [Unity ML-Agents GitHub Repository](https://github.com/Unity-Technologies/ml-agents).\nAll rights to these examples belong to Unity Technologies. We claim no ownership over them.\n\n#### Dependencies\n1. **Unity side**: ML-Agents 2.0.1 (installed automatically via Unity Package Manager)\n2. **Python side**: Dennis Soemers’ [ML-Agents fork](https://www.github.com/dennissoemers/ml-agents)\n\n### License Notice\nThe Unity ML-Agents Examples included here remain under their original [Apache License, Version 2.0](https://www.apache.org/licenses/LICENSE-2.0), as provided by Unity Technologies. All other code and assets created for this repository are licensed under the terms specified in this project’s LICENSE file.\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomarelfiki%2Funity-ml-drl-data","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fomarelfiki%2Funity-ml-drl-data","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fomarelfiki%2Funity-ml-drl-data/lists"}