asieradzk/RL_Matrix

Deep Reinforcement Learning in C#

42
/ 100
Emerging

Built on TorchSharp, it implements state-of-the-art algorithms (PPO, DQN variants up to Rainbow, GAIL) with native C# type safety and outperforms Python baselines. Features include multi-head action space support, RNN integration for partial observability, distributed multi-environment training, and built-in real-time dashboards. Integrates directly with Unity and Godot engines via source generation that simplifies complex RL workflows.

302 stars. No commits in the last 6 months.

Stale 6m No Package No Dependents
Maintenance 2 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 14 / 25

How are scores calculated?

Stars

302

Forks

27

Language

C#

License

Last pushed

Jul 04, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/agents/asieradzk/RL_Matrix"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.