Материал на языке оригинала: English.
Evolution strategies as a scalable alternative to reinforcement learning
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.
24 марта 2017 г. · Источник: OpenAI news
Полный текст доступен у источника.