shipfeedAI news, curated daily

01:22:43 CET
21 MAY01:22:43shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Evolution strategies as a scalable alternative to reinforcement learning

OpenAI finds evolution strategies match standard reinforcement learning performance on Atari and MuJoCo benchmarks while avoiding several common RL drawbacks.

Mar 24 · · primary fetch1 sourceupdated Mar 24 ·

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.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comEvolution strategies as a scalable alternative to reinforcement learningprimary