Class UInferencePolicy

class UInferencePolicy : public UAbstractPolicy

Policy that uses a trained NNE model to make decisions.

Public Functions

UInferencePolicy()
TArray<FString> GetRuntimeNames() const

Function that grabs all availabe runtime names.

Returns:

An Array of available runtime names

IRuntimeInterface *GetRuntime(const FString &SelectedRuntimeName) const

Function that gets the singleton instance of the runtime with the given name.

Parameters:

SelectedRuntimeName[in] The name of the runtime to get

Returns:

A ptr to the runtime with the given name

virtual TFuture<FPolicyDecision*> RequestDecision(const FDictPoint &Observations) override

Request that the policy decide on action.

May take some time to occur

Parameters:

Observations[in] The current state of the agent used to inform the policies choice of action

Returns:

A future that will eventually contain the policy’s next decision

virtual void Init(const FInteractionDefinition &PolicyDefinition)

Initialize an instance of a policy object from an interaction definition.

Parameters:

PolicyDefinition[in] An object defining the policy’s I/O shapes and other parameters

Public Members

int Step = 0

Number of inference calls to the policy.

FDictSpace ActionSpaceDefn

The Action Space of the Agent.

FDictSpace ObservationSpaceDefn

The Observation Space of the Agent.

TObjectPtr<UNNEModelData> ModelData

The Model Data for the NNE Model.

FString RuntimeName

The Name of the Runtime to use for Inference.

If no Runtimes are available, enable NNE plugins (e.g. NNERuntimeORT)

bool bNetworkLoaded = false

Variable tracking if the network loaded correctly?

TArray<float> ActionBuffer
TArray<float> ObservationBuffer

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!