FRLlibAPPOSettings
struct FRLlibAPPOSettings : public FTrainingSettings
A struct to hold Asynchronous Proximal Policy Optimization(APPO) settings for an RLLib training script.
Note: This is a partial implementation of the APPO settings, and is not exhaustive
Dependencies: FScriptArgBuilder, FTrainingSettings
Inherits from: public FTrainingSettings
Public Interface
Destructor:
~FRLlibAPPOSettings
virtual ~FRLlibAPPOSettings()
Attributes: virtual
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 40, column 9)
Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.cpp
(lines 15-18)
Public Functions:
GenerateTrainingArgs
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 scriptArgBuilder
(FScriptArgBuilder &
) – [in] The builder to use to generate the arguments
Attributes: const
, virtual
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 38, column 6)
Implementation: Schola/Source/Schola/Private/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.cpp
(lines 5-13)
Public Members:
bool bVTrace
bool bVTrace = = true
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 21, column 10)
float VTraceClipRhoThreshold
float VTraceClipRhoThreshold = = 1.0
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 24, column 11)
float VTraceClipPGRhoThreshold
float VTraceClipPGRhoThreshold = = 1.0
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 27, column 11)
float GAELambda
float GAELambda = = 0.95
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 30, column 11)
float ClipParam
float ClipParam = = 0.2
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 33, column 11)
bool bUseGAE
bool bUseGAE = = true
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 36, column 10)
Used By: FRLlibTrainingSettings
Source: Schola/Source/Schola/Public/Subsystem/SubsystemSettings/Ray/Algorithms/RLlibAPPOSettings.h
(line 15, column 1)