|
| template<typename It > |
| int | exploration::generate_epsilon_greedy (float epsilon, uint32_t top_action, It pmf_first, It pmf_last) |
| | Generates epsilon-greedy style exploration distribution. More...
|
| |
| template<typename InputIt , typename OutputIt > |
| int | exploration::generate_softmax (float lambda, InputIt scores_first, InputIt scores_last, OutputIt pmf_first, OutputIt pmf_last) |
| | Generates softmax style exploration distribution. More...
|
| |
| template<typename InputIt , typename OutputIt > |
| int | exploration::generate_bag (InputIt top_actions_first, InputIt top_actions_last, OutputIt pmf_first, OutputIt pmf_last) |
| | Generates an exploration distribution according to votes on actions. More...
|
| |
| template<typename It > |
| int | exploration::enforce_minimum_probability (float minimum_uniform, bool update_zero_elements, It pmf_first, It pmf_last) |
| | Updates the pmf to ensure each action is explored with at least minimum_uniform/num_actions. More...
|
| |
| template<typename It > |
| int | exploration::sample_after_normalizing (uint64_t seed, It pmf_first, It pmf_last, uint32_t &chosen_index) |
| | Sample an index from the provided pmf. If the pmf is not normalized it will be updated in-place. More...
|
| |
| template<typename It > |
| int | exploration::sample_after_normalizing (const char *seed, It pmf_first, It pmf_last, uint32_t &chosen_index) |
| | Sample an index from the provided pmf. If the pmf is not normalized it will be updated in-place. More...
|
| |
| template<typename ActionIt > |
| int | exploration::swap_chosen (ActionIt action_first, ActionIt action_last, uint32_t chosen_index) |
| | Swap the first value with the chosen index. More...
|
| |
| template<typename It > |
| int | exploration::sample_pdf (uint64_t *p_seed, It pdf_first, It pdf_last, float &chosen_value, float &pdf_value) |
| | Sample a continuous value from the provided pdf. More...
|
| |
