10 #ifdef LIBTORCH_ENABLED 22 params.
addClassDescription(
"Reporter containing the reward values of a DRL controller trainer.");
24 "drl_trainer_name",
"The name of the RDL controller trainer which computes the rewards.");
Real averageEpisodeReward()
Function which returns the current average episodic reward.
Real & _reward
The reward values which will be saved.
const ReporterMode REPORTER_MODE_ROOT
DRLRewardReporter(const InputParameters ¶meters)
static InputParameters validParams()
registerMooseObject("StochasticToolsApp", DRLRewardReporter)
Reporter which saves the reward values from a Deep Reinforcement Learning controller trainer...
static InputParameters validParams()
LibtorchDRLControlTrainer & _trainer
The DRL trainer which computes the reward values.
DIE A HORRIBLE DEATH HERE typedef LIBMESH_DEFAULT_SCALAR_TYPE Real
Interface for objects that need to use samplers.
This trainer is responsible for training neural networks that efficiently control different processes...
static InputParameters validParams()
virtual void execute() override