|
bitrl & cuberl Documentation
Simulation engine for reinforcement learning agents
|
Namespaces | |
| namespace | agents |
| namespace | algos |
| namespace | envs |
| namespace | policies |
Classes | |
| struct | ConstantLRScheduler |
| struct ConstantLRScheduler. Echos bach the learning rate it was given More... | |
| struct | EpisodeInfo |
| The EpisodeInfo struct. More... | |
| class | RLSerialAgentTrainer |
| struct | RLSerialTrainerConfig |
| The RLSerialTrainerConfig struct. Configuration struct for the serial RL agent trainer. More... | |
| struct | with_decay_epsilon_option_mixin |
| The with_decay_epsilon_option_mixin struct. More... | |
| struct | with_double_q_table_max_action_mixin |
| struct | with_double_q_table_mixin |
| struct | with_double_q_table_mixin< DynMat< real_t > > |
| The WithDoubleQTableMixin struct. More... | |
| struct | with_double_q_table_mixin< std::map< KeyTp, DynVec< real_t > > > |
| struct | with_q_table_mixin |
| The WithQTableMixin struct. More... | |
Functions | |
| std::ostream & | operator<< (std::ostream &out, const EpisodeInfo &info) |
| BETTER_ENUM (EpsilonDecayOptionType, char, INVALID_TYPE=0, NONE, EXPONENTIAL, INVERSE_STEP, CONSTANT_RATE) | |
| The RenderModeType enum. | |
| std::string | to_string (EpsilonDecayOptionType type) |
| to_string. Returns the RenderModeType to its stringrepresentation | |
| uint_t | max_action (const DynMat< real_t > &qtable, uint_t state, uint_t n_actions) |
| max_action | |
Utility class used in the implementation of RL algorithms
| cuberl::rl::BETTER_ENUM | ( | EpsilonDecayOptionType | , |
| char | , | ||
| INVALID_TYPE | = 0, |
||
| NONE | , | ||
| EXPONENTIAL | , | ||
| INVERSE_STEP | , | ||
| CONSTANT_RATE | |||
| ) |
The RenderModeType enum.
max_action
| qtable | |
| state | |
| n_actions |
|
inline |
|
inline |
to_string. Returns the RenderModeType to its stringrepresentation
| type | The RenderModeType to convert |