10 #ifndef REINFORCEDLEARNING_H 11 #define REINFORCEDLEARNING_H 32 class RlBackupAlgorithm;
38 static constexpr
const char *
configKey =
"reinforcedLearning";
57 double discountFactor{0.1};
Utils::Record rewardRecord
ActionValuesFunction * actionValues
RlBackupAlgorithm * backupAlgo
ActionValuesRecord actionValuesRecord
action_t getBestActionFromInitialPolicy(state_t s)
void updatePolicy(state_t state)
void updateLongTermReward(double reward, double discountFactor)
RlBackupAlgorithm * getBackupAlgorithm()
static constexpr const char * configKey
action_t getBestAction(state_t state)
double actualDiscountedReward
ActionSelectionStrategy * actionSelectionStrategy
void epsilonGreedyPolicyUpdate(state_t state)
void printActionValuesToFile(std::string folder)
ReinforcedLearning(std::shared_ptr< Context > context)
void updateActualDiscountedReward(double reward)
std::shared_ptr< Context > context
long long unsigned int epsilonTimeOut
void initializeActionSelectionStrategy()