AMD announced today the release of Schola 1.0 as an open-source reinforcement learning library that is being made available under an MIT license and as part of their GPUOpen software collection for helping game developers.

AMD Schola is self-described as:

"The Schola project is an effort to build a toolkit/plugin for controlling Objects in Unreal with Reinforcement Learning. It provides tools to help the user create Environments, define Agents, connect to python based RL Frameworks (e.g. Gym, RLLib or Stable Baselines 3), and power NPCs with RL during games."

For now at least this Schola library is sadly limited to Unreal Engine 5.4+ integration and not any other game engines. But the code is open-source under an MIT license.

Schola 1.0 features include inference support with agents via ONNX models, headless training, multi-agent training, vectorized training, and other features. Great seeing AMD continuing to up their software game.

Those wanting to learn about this open-source AMD Schola project can do so via [1]GPUOpen.com and the [2]Schola repository on GitHub .



[1] https://gpuopen.com/amd-schola/

[2] https://github.com/GPUOpen-LibrariesAndSDKs/Schola/releases/tag/v1.0.0