 |
обучение с подкреплением
| на основе
| человеческих
| предпочтений
| обучение с подкреплением | |
| AI. | RL; reinforcement learning |
| на основе | |
| gen. | predicated on; on the bedrock of |
| archit. | inspired by |
| Makarov. | assisted |
| offic. | in respect of |
| на основе DDU | |
| logist. | on a DDU basis |
| на основе SQL | |
| comp., MS | SQL based |
| человеческий | |
| gen. | human |
| предпочтение | |
| gen. | preference |
| |||
RL (сокр. от "reinforcement learning" Alex_Odeychuk); reinforcement learning (a type of machine learning that enables a system to learn by trial and error using feedback from its own actions  singularityhub.com Dmitrarka) | |||
| reward training | |||
| обучение с подкреплением: 22 phrases in 5 subjects |
| Artificial intelligence | 13 |
| Makarov | 4 |
| Neural networks | 1 |
| Programming | 3 |
| Scientific | 1 |