mlpack
Public Member Functions | List of all members
mlpack::rl::TrainingConfig Class Reference

Public Member Functions

 TrainingConfig (size_t numWorkers, size_t updateInterval, size_t targetNetworkSyncInterval, size_t stepLimit, size_t explorationSteps, double stepSize, double discount, double gradientLimit, bool doubleQLearning, bool noisyQLearning, bool isCategorical, size_t atomSize, double vMin, double vMax, double rho)
 
size_t NumWorkers () const
 Get the amount of workers.
 
size_t & NumWorkers ()
 Modify the amount of workers.
 
size_t UpdateInterval () const
 Get the update interval.
 
size_t & UpdateInterval ()
 Modify the update interval.
 
size_t TargetNetworkSyncInterval () const
 Get the interval for syncing target network.
 
size_t & TargetNetworkSyncInterval ()
 Modify the interval for syncing target network.
 
size_t StepLimit () const
 Get the maximum steps of each episode.
 
size_t & StepLimit ()
 Modify the maximum steps of each episode. More...
 
size_t ExplorationSteps () const
 Get the exploration steps.
 
size_t & ExplorationSteps ()
 Modify the exploration steps.
 
double StepSize () const
 Get the step size of the optimizer.
 
double & StepSize ()
 Modify the step size of the optimizer.
 
double Discount () const
 Get the discount rate for future reward.
 
double & Discount ()
 Modify the discount rate for future reward.
 
double GradientLimit () const
 Get the limit of update gradient.
 
double & GradientLimit ()
 Modify the limit of update gradient.
 
bool DoubleQLearning () const
 Get the indicator of double q-learning.
 
bool & DoubleQLearning ()
 Modify the indicator of double q-learning.
 
bool NoisyQLearning () const
 Get the indicator of noisy q-learning.
 
bool & NoisyQLearning ()
 Modify the indicator of double q-learning.
 
bool IsCategorical () const
 Get the indicator of categorical q-learning.
 
bool & IsCategorical ()
 Modify the indicator of categorical q-learning.
 
size_t AtomSize () const
 Get the number of atoms.
 
size_t & AtomSize ()
 Modify the number of atoms.
 
double VMin () const
 Get the minimum value for support.
 
double & VMin ()
 Modify the minimum value for support.
 
double VMax () const
 Get the maximum value for support.
 
double & VMax ()
 Modify the maximum value for support.
 
double Rho () const
 Get the rho value for sac.
 
double & Rho ()
 Modify the rho value for sac.
 

Member Function Documentation

◆ StepLimit()

size_t& mlpack::rl::TrainingConfig::StepLimit ( )
inline

Modify the maximum steps of each episode.

Setting it to 0 means no limit.


The documentation for this class was generated from the following file: