News for hackers. Stuff that matters.
Re:The use of embeddings in OpenAI Five by backpropaganda on Friday September 14, 2018 @01:00AM (#17984779)
At a competent level? None exist. Being better than random doesn't count as competency. As others have said in this thread, it wouldn't even pass as median performance.

> is only helping to advance the state of reinforcement learning

Zero new algorithms or ideas were introduced by OpenAI Five. We just learn that model-free RL doesn't scale and we already knew that from Atari and robotics benchmarks.

There are no comments on this comment yet.