Class UPythonGymConnector

class UPythonGymConnector : public UExternalGymConnector

A connection to an external gym API that is implemented in python, using gRPC for communication.

Note

This can theoretically work with any gRPC client not just python although that is untested currently.

Public Functions

UPythonGymConnector()

Create a new UPythonGymConnector.

virtual TFuture<FTrainingStateUpdate*> RequestStateUpdate() override

Request a decision from gym using the current state of the agents from environments.

Note

This function is asynchronous and will return immediately

Returns:

A future that will eventually contain decision for all agents in all environments

virtual void SendState(const FTrainingState &Value) override

Send the state of the environment to gym.

Note

This function should be implemented by any derived classes

Parameters:

Value[in] The state of the environment

virtual void SubmitPostResetState(const FTrainingState &Value) override

Submit the initial state of the environment after a reset to the other end of the connector.

Note

This function should be implemented by a derived class

Parameters:

States[in] The states to submit

virtual void Init(const FSharedTrainingDefinition &AgentDefns) override

Initialize this gym connector, setting up services and sending agent definitions.

Note

This function should be implemented by a derived class

Parameters:

AgentDefinitions – – The definitions of the agents that will be trained

virtual void Enable() override

Enable the connector.

Useful for multistage setup as it is called after init.

Note

This function should be implemented by a derived class

virtual bool CheckForStart() override

Check if the connector is ready to start.

Note

This function should be implemented by a derived class

Returns:

True if the connector is ready to start

Related pages

  • Visit the Schola product page for download links and more information.

Looking for more documentation on GPUOpen?

AMD GPUOpen software blogs

Our handy software release blogs will help you make good use of our tools, SDKs, and effects, as well as sharing the latest features with new releases.

GPUOpen Manuals

Don’t miss our manual documentation! And if slide decks are what you’re after, you’ll find 100+ of our finest presentations here.

AMD GPUOpen Performance Guides

The home of great performance and optimization advice for AMD RDNA™ 2 GPUs, AMD Ryzen™ CPUs, and so much more.

Getting started: AMD GPUOpen software

New or fairly new to AMD’s tools, libraries, and effects? This is the best place to get started on GPUOpen!

AMD GPUOpen Getting Started Development and Performance

Looking for tips on getting started with developing and/or optimizing your game, whether on AMD hardware or generally? We’ve got you covered!

AMD GPUOpen Technical blogs

Browse our technical blogs, and find valuable advice on developing with AMD hardware, ray tracing, Vulkan®, DirectX®, Unreal Engine, and lots more.

Find out more about our software!

AMD GPUOpen Effects - AMD FidelityFX technologies

Create wonder. No black boxes. Meet the AMD FidelityFX SDK!

AMD GPUOpen Samples

Browse all our useful samples. Perfect for when you’re needing to get started, want to integrate one of our libraries, and much more.

AMD GPUOpen developer SDKs

Discover what our SDK technologies can offer you. Query hardware or software, manage memory, create rendering applications or machine learning, and much more!

AMD GPUOpen Developer Tools

Analyze, Optimize, Profile, Benchmark. We provide you with the developer tools you need to make sure your game is the best it can be!