Function cselect_child

core/ctree/cnode.cpp:327–352

    }

    int cselect_child(CNode* root, tools::CMinMaxStats &min_max_stats, int pb_c_base, float pb_c_init, float discount, float mean_q){
        float max_score = FLOAT_MIN;
        const float epsilon = 0.000001;
        std::vector<int> max_index_lst;
        for(int a = 0; a < root->action_num; ++a){
            CNode* child = root->get_child(a);
            float temp_score = cucb_score(child, min_max_stats, mean_q, root->is_reset, root->visit_count - 1, root->value_prefix, pb_c_base, pb_c_init, discount);

            if(max_score < temp_score){
                max_score = temp_score;

                max_index_lst.clear();
                max_index_lst.push_back(a);
            }
            else if(temp_score >= max_score - epsilon){
                max_index_lst.push_back(a);
            }
        }

        int action = 0;
        if(max_index_lst.size() > 0){
            int rand_index = rand() % max_index_lst.size();
            action = max_index_lst[rand_index];
        }
        return action;
    }

    float cucb_score(CNode *child, tools::CMinMaxStats &min_max_stats, float parent_mean_q, int is_reset, float total_children_visit_counts, float parent_value_prefix, float pb_c_base, float pb_c_init, float discount){
        float pb_c = 0.0, prior_score = 0.0, value_score = 0.0;