All News
Neural Networks

Evolution strategies as a scalable alternative to reinforcement learning

March 24, 20170 views1 min read

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.

Want to try AI?

Compare the best neural networks in one place — for free

Go to neural networks
Share:
Источник: OpenAI Blog

Related News