shipfeedAI news, curated daily

00:33:31 CET
21 MAY00:33:31shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

Better exploration with parameter noise

OpenAI publishes findings that adding adaptive parameter noise to reinforcement learning algorithms frequently boosts exploration performance with minimal downside risk.

Jul 27 · · primary fetch1 sourceupdated Jul 27 ·

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance.

This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comBetter exploration with parameter noiseprimary