{"id":28633913,"url":"https://github.com/matrixsmaster/flappy_neat","last_synced_at":"2025-10-13T17:06:46.106Z","repository":{"id":298200637,"uuid":"999176599","full_name":"matrixsmaster/flappy_neat","owner":"matrixsmaster","description":"Flappy NEAT is a testbench where neural networks learn to play a game using a mix of genetic neuro-evolution and reinforcement learning.","archived":false,"fork":false,"pushed_at":"2025-06-15T11:46:57.000Z","size":320,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"master","last_synced_at":"2025-08-05T15:40:07.981Z","etag":null,"topics":["ai","delphi7","genetic-algorithm","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"Pascal","has_issues":false,"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/matrixsmaster.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}},"created_at":"2025-06-09T21:22:50.000Z","updated_at":"2025-06-15T11:24:37.000Z","dependencies_parsed_at":"2025-06-09T23:31:00.352Z","dependency_job_id":"8c20cfd6-3a56-4d44-9153-815131491a70","html_url":"https://github.com/matrixsmaster/flappy_neat","commit_stats":null,"previous_names":["matrixsmaster/flappy_neat"],"tags_count":3,"template":false,"template_full_name":null,"purl":"pkg:github/matrixsmaster/flappy_neat","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matrixsmaster%2Fflappy_neat","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matrixsmaster%2Fflappy_neat/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matrixsmaster%2Fflappy_neat/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matrixsmaster%2Fflappy_neat/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/matrixsmaster","download_url":"https://codeload.github.com/matrixsmaster/flappy_neat/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/matrixsmaster%2Fflappy_neat/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279016282,"owners_count":26085827,"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":"2025-10-13T02:00:06.723Z","response_time":61,"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":["ai","delphi7","genetic-algorithm","reinforcement-learning"],"created_at":"2025-06-12T15:39:32.549Z","updated_at":"2025-10-13T17:06:46.084Z","avatar_url":"https://github.com/matrixsmaster.png","language":"Pascal","funding_links":[],"categories":[],"sub_categories":[],"readme":"# 🐤 Flappy NEAT\n\n\u003cimg src=\"img/screenshot01.jpg\" alt=\"screenshot\" style=\"max-width: 100%; height: auto; display: block;\" /\u003e\n\n**Flappy NEAT** is a chaotic little testbench where neural networks learn to play a Flappy Bird–style game using a mix of **genetic neuro-evolution** and **reinforcement learning**. It’s designed to let you:\n\n- Compare **human**, **algorithmic**, **neuro-evolved**, and **RL-trained** performance\n- Seamlessly switch from **evolution** to **RL fine-tuning** once a score threshold is hit\n- Experiment with unique genetic operators and learning tricks you've probably never seen before\n\nIt’s a research toy, a performance benchmark, and a testbed for weird ideas—all in one.\n\n---\n\n## 🧠 Highlights\n\n- 🚀 **Alpha-selection**: A novel genetic operator to drive better diversity\n- 🔥 **Neuron heat dynamics**: RL weight updates are modulated by how “hot” neurons are\n- 🧬 **Custom crossover/inversion/mutation logic**\n- 🎩 **Interactive human mode** for score comparison\n- 🤖 **Algorithmic solver mode** (perfect agent)\n- 🧪 **Experimental PPO-inspired RL strategy**\n- 🔀 **Hybrid GA → RL transition** based on fitness threshold\n- 🛠️ **Live UI** with parameter tweaking\n- 📚 **Help system** built into the UI with all information needed to understand every parameter\n- 🔄 **Save/load for agents and populations**\n- 🌍 **Neural network visualization and weight matrix viewer**\n- 🕛 **Scenario replay support for post-mortem analysis**\n\n---\n\n## 🛠️ Running the Project\n\n### A precompiled `.exe` is provided with each release - you can run it directly in windows or WINE.\n\nThis program was built using **Delphi 7**, which means:\n\n\u003e ⚠️ You will need a **Windows XP environment** with **Delphi 7** installed to compile and run this project.\n\nWe recommend spinning up a virtual machine for this purpose. Nostalgia points are included for free.\n\n---\n\n## 🧪 Sample Use Case\n\nTrain a population to solve the level using evolution, then transition into RL for fine-tuning behavior. Compare its score to your own flapping skills, or the perfect algorithmic solver. Discover if your `AlphaSort` operator beats standard crossover methods. Watch neuron \"heat maps\" influence updates. Or just... create a mutant bird that flaps with pure chaos.\n\nHint: Try to use test INI files provided in the repo.\n\n### (C) Dmitry 'MatrixS_Master' Solovyev, 2025\n\n### License: GPL v3\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatrixsmaster%2Fflappy_neat","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fmatrixsmaster%2Fflappy_neat","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fmatrixsmaster%2Fflappy_neat/lists"}