{"id":50475986,"url":"https://github.com/dron3flyv3r/rl-agent-plugin","last_synced_at":"2026-06-01T13:03:29.670Z","repository":{"id":347566394,"uuid":"1192593218","full_name":"dron3flyv3r/rl-agent-plugin","owner":"dron3flyv3r","description":"An RL Agent system with in-editor training and control. Single-/Multi-agent support.","archived":false,"fork":false,"pushed_at":"2026-04-17T19:26:44.000Z","size":3229,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2026-04-17T20:15:56.260Z","etag":null,"topics":["csharp","godot","multi-agent","reinforcement-learning"],"latest_commit_sha":null,"homepage":"","language":"C#","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dron3flyv3r.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","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":"2026-03-26T11:20:56.000Z","updated_at":"2026-04-17T19:26:47.000Z","dependencies_parsed_at":null,"dependency_job_id":null,"html_url":"https://github.com/dron3flyv3r/rl-agent-plugin","commit_stats":null,"previous_names":["dron3flyv3r/rl-agent-plugin"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/dron3flyv3r/rl-agent-plugin","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dron3flyv3r%2Frl-agent-plugin","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dron3flyv3r%2Frl-agent-plugin/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dron3flyv3r%2Frl-agent-plugin/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dron3flyv3r%2Frl-agent-plugin/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dron3flyv3r","download_url":"https://codeload.github.com/dron3flyv3r/rl-agent-plugin/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dron3flyv3r%2Frl-agent-plugin/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":33775865,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-06-01T02:00:06.963Z","response_time":115,"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":["csharp","godot","multi-agent","reinforcement-learning"],"created_at":"2026-06-01T13:03:28.617Z","updated_at":"2026-06-01T13:03:29.659Z","avatar_url":"https://github.com/dron3flyv3r.png","language":"C#","funding_links":[],"categories":[],"sub_categories":[],"readme":"# RL Agent Plugin for Godot 4\n\nReinforcement learning plugin for Godot 4 with in-editor training, live metrics, curriculum learning, self-play, distributed rollout workers, and `.rlmodel` export for inference.\n\n## Features\n\n- PPO, A2C, SAC, DQN, and MCTS trainers\n- Shared policy groups across multiple agents\n- Recurrent LSTM and GRU trunk layers for PPO/A2C\n- RL editor tooling: `RLDash` and `RL Setup` dock\n- Curriculum and self-play configuration resources\n- Distributed rollout collection with headless workers\n- Binary `.rlmodel` export/import for deployment\n\n## Requirements\n\n- Godot 4.6+ with C# support\n- .NET SDK 8.0+\n\n## Install in a Godot project\n\nLatest stable release in this line: `v0.2.0-beta`\n\nOption A: copy plugin folder\n\n1. Copy this repository into your game project as `addons/rl-agent-plugin`.\n2. Open Godot -\u003e Project Settings -\u003e Plugins.\n4. Build once (`Alt+B`).\n3. Enable `RL Agent Plugin`.\n4. if RLDash aren't showing in the editor, restart the editor.\n\nOption B: add as submodule\n\n```bash\ngit submodule add https://github.com/dron3flyv3r/rl-agent-plugin.git addons/rl-agent-plugin\ngit submodule update --init --recursive\ngit -C addons/rl-agent-plugin fetch --tags\ngit -C addons/rl-agent-plugin checkout v0.2.0-beta\n```\n\nOptional (bleeding edge): track `main` instead of a release tag.\n\n## Upgrade to a newer release\n\nIf you installed as a submodule, update to a newer tagged release with:\n\n```bash\ngit -C addons/rl-agent-plugin fetch --tags\ngit -C addons/rl-agent-plugin switch \u003cnew-release-tag\u003e\ngit add addons/rl-agent-plugin\n```\n\nExample:\n\n```bash\ngit -C addons/rl-agent-plugin fetch --tags\ngit -C addons/rl-agent-plugin switch v0.2.0-beta\ngit add addons/rl-agent-plugin\n```\n\nTo list available tags:\n\n```bash\ngit -C addons/rl-agent-plugin tag --list\n```\n\n## Quick usage\n\n1. Add an `RLAcademy` node in your training scene.\n2. Add one or more `RLAgent2D` or `RLAgent3D` nodes.\n3. Assign `RLTrainingConfig`, `RLRunConfig`, and per-agent `PolicyGroupConfig` resources.\n4. Start training from toolbar (`Start Training`) or `RL Setup` dock.\n5. Monitor metrics in `RLDash`.\n6. Export checkpoints to `.rlmodel`.\n\n## Documentation\n\n- Docs index: `docs/README.md`\n- Feature catalog: `docs/features.md`\n- Get started: `docs/get-started.md`\n- Configuration reference: `docs/configuration.md`\n- Architecture: `docs/architecture.md`\n- Algorithms: `docs/algorithms.md`\n- Native build + validation: `docs/build-native.md`\n- Tuning: `docs/tuning.md`\n\n## Companion demo project\n\nIf you want ready-to-run demo scenes, use:\n\n- https://github.com/dron3flyv3r/rl-agent-godot\n\nThat repo contains training environments and example game scenes that consume this plugin.\n\n## License\n\nMIT\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdron3flyv3r%2Frl-agent-plugin","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdron3flyv3r%2Frl-agent-plugin","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdron3flyv3r%2Frl-agent-plugin/lists"}