Evolution strategies as a scalable alternative to reinforcement learning
- ID
- 986
- Status
- new
- Published
- 24 Mar 2017, 3:00 PM
- Fetched
- 27 Jun 2026, 7:47 PM
- Provider
- OpenAI News
- Category
- ai-labs
- Original URL
- https://openai.com/index/evolution-strategies
- Source URL
- https://openai.com/news/rss.xml
Excerpt
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.
Summary
No summary yet. It will appear after the daemon summarizes this item.