bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
Loading...
Searching...
No Matches
cuberl::rl::algos::td::QLearningConfig Struct Reference

The QLearningConfig struct. More...

#include <q_learning.h>

Public Attributes

bool average_episode_reward {true}
 
uint_t n_episodes
 
uint_t max_num_iterations_per_episode
 
real_t tolerance
 
real_t gamma
 
real_t eta
 
std::string path {bitrl::consts::INVALID_STR}
 

Detailed Description

The QLearningConfig struct.

Member Data Documentation

◆ average_episode_reward

bool cuberl::rl::algos::td::QLearningConfig::average_episode_reward {true}

◆ eta

real_t cuberl::rl::algos::td::QLearningConfig::eta

◆ gamma

real_t cuberl::rl::algos::td::QLearningConfig::gamma

◆ max_num_iterations_per_episode

uint_t cuberl::rl::algos::td::QLearningConfig::max_num_iterations_per_episode

◆ n_episodes

uint_t cuberl::rl::algos::td::QLearningConfig::n_episodes

◆ path

std::string cuberl::rl::algos::td::QLearningConfig::path {bitrl::consts::INVALID_STR}

◆ tolerance

real_t cuberl::rl::algos::td::QLearningConfig::tolerance

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