FRLlibPPOSettings

struct FRLlibPPOSettings : public FTrainingSettings

A struct to hold Proximal Policy Optimization(PPO) settings for an RLLib training script.

Note: This is a partial implementation of the PPO settings, and is not exhaustive

Dependencies: FScriptArgBuilder, FTrainingSettings

Inherits from: public FTrainingSettings

Public Interface

Destructor:

virtual ~FRLlibPPOSettings()

Attributes: virtual

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.h (line 31, column 9)

Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.cpp (lines 13-16)

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/Algorithms/RLlibPPOSettings.h (line 29, column 6)

Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.cpp (lines 5-11)

Public Members:

float GAELambda = = 0.95

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.h (line 21, column 11)

float ClipParam = = 0.2

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.h (line 24, column 11)

bool bUseGAE = = true

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.h (line 27, column 10)

Used By: FRLlibTrainingSettings

Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibPPOSettings.h (line 15, column 1)