Reinforcement learning plugin for Godot 4 with in-editor training, live metrics, curriculum learning, self-play, distributed rollout workers, and .rlmodel export for inference.
- PPO, A2C, SAC, DQN, and MCTS trainers
- Shared policy groups across multiple agents
- Recurrent LSTM and GRU trunk layers for PPO/A2C
- RL editor tooling:
RLDashandRL Setupdock - Curriculum and self-play configuration resources
- Distributed rollout collection with headless workers
- Binary
.rlmodelexport/import for deployment
- Godot 4.6+ with C# support
- .NET SDK 8.0+
Latest stable release in this line: v0.2.0-beta
Option A: copy plugin folder
- Copy this repository into your game project as
addons/rl-agent-plugin. - Open Godot -> Project Settings -> Plugins.
- Build once (
Alt+B). - Enable
RL Agent Plugin. - if RLDash aren't showing in the editor, restart the editor.
Option B: add as submodule
git submodule add https://github.com/dron3flyv3r/rl-agent-plugin.git addons/rl-agent-plugin
git submodule update --init --recursive
git -C addons/rl-agent-plugin fetch --tags
git -C addons/rl-agent-plugin checkout v0.2.0-betaOptional (bleeding edge): track main instead of a release tag.
If you installed as a submodule, update to a newer tagged release with:
git -C addons/rl-agent-plugin fetch --tags
git -C addons/rl-agent-plugin switch <new-release-tag>
git add addons/rl-agent-pluginExample:
git -C addons/rl-agent-plugin fetch --tags
git -C addons/rl-agent-plugin switch v0.2.0-beta
git add addons/rl-agent-pluginTo list available tags:
git -C addons/rl-agent-plugin tag --list- Add an
RLAcademynode in your training scene. - Add one or more
RLAgent2DorRLAgent3Dnodes. - Assign
RLTrainingConfig,RLRunConfig, and per-agentPolicyGroupConfigresources. - Start training from toolbar (
Start Training) orRL Setupdock. - Monitor metrics in
RLDash. - Export checkpoints to
.rlmodel.
- Docs index:
docs/README.md - Feature catalog:
docs/features.md - Get started:
docs/get-started.md - Configuration reference:
docs/configuration.md - Architecture:
docs/architecture.md - Algorithms:
docs/algorithms.md - Native build + validation:
docs/build-native.md - Tuning:
docs/tuning.md
If you want ready-to-run demo scenes, use:
That repo contains training environments and example game scenes that consume this plugin.
MIT