shipfeedAI news, curated daily

00:33:18 CET
21 MAY00:33:18shipfeed
pull to refreshlast sync
Just in — 30 new
§ feed · storyline

OpenAI Baselines: ACKTR & A2C

OpenAI releases two reinforcement learning baseline implementations, A2C and ACKTR, with ACKTR offering improved sample efficiency over TRPO and A2C at modest additional compute cost.

Aug 18 · · primary fetch1 sourceupdated Aug 18 ·

We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal performance.

ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.

read full article on openai.com
§ sources1 publication · timeline below
  1. openai.comOpenAI Baselines: ACKTR & A2Cprimary