FRLlibNetworkArchSettings

struct FRLlibNetworkArchSettings : public FTrainingSettings

A struct to hold network architecture settings for an RLlib training script.

Dependencies: FScriptArgBuilder, FTrainingSettings

Inherits from: public FTrainingSettings

Public Interface

Destructor:

virtual ~FRLlibNetworkArchSettings()

Attributes: virtual

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 51, column 9)

Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.cpp (lines 31-33)

Public Functions:

virtual void GenerateTrainingArgs(int Port, FScriptArgBuilder &ArgBuilder) const const

Generate the training arguments for the script using the ArgBuilder.

Note: port is supplied as it is a common argument to pass to scripts, and is set at a high level but might be needed by specific subsettings

Parameters:

Port (int) – [in] The port to use for the script
ArgBuilder (FScriptArgBuilder &) – [in] The builder to use to generate the arguments

Attributes: const, virtual

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 49, column 6)

Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.cpp (lines 6-29)

Public Members:

ERLlibActivationFunctionEnum ActivationFunction = = ERLlibActivationFunctionEnum::ReLU

The activation function to use in the neural network.

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 31, column 30)

TArray<int> FCNetHiddens = = &#123; 512, 512 &#125;

The number and width of hidden layers in the neural network.

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 35, column 8)

int MinibatchSize = = 256

The size of each minibatch.

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 39, column 5)

bool bUseAttention = = false

Whether to use attention in the model.

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 43, column 6)

int AttentionDims = = 64

The dimension of the attention layer.

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 47, column 5)

Used By: FRLlibTrainingSettings

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/RLlibNetworkArchitectureSettings.h (line 24, column 1)