|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
#include "cuberl/base/cubeai_config.h"#include "cuberl/base/cuberl_types.h"#include "cuberl/rl/epsilon_decay_options.h"#include <map>#include <tuple>#include <random>
Go to the source code of this file.
Classes | |
| struct | cuberl::rl::with_decay_epsilon_option_mixin |
| The with_decay_epsilon_option_mixin struct. More... | |
| struct | cuberl::rl::with_q_table_mixin |
| The WithQTableMixin struct. More... | |
| struct | cuberl::rl::with_double_q_table_mixin< DynMat< real_t > > |
| The WithDoubleQTableMixin struct. More... | |
| struct | cuberl::rl::with_double_q_table_mixin< std::map< KeyTp, DynVec< real_t > > > |
| struct | cuberl::rl::with_double_q_table_max_action_mixin |
Namespaces | |
| namespace | cuberl |
| Various utilities used when working with RL problems. | |
| namespace | cuberl::rl |
Functions | |
| uint_t | cuberl::rl::max_action (const DynMat< real_t > &qtable, uint_t state, uint_t n_actions) |
| max_action | |