Evolution Strategies as a Scalable Alternative to Reinforcement Learning · HackerPapers discussions

Evolution Strategies as a Scalable Alternative to Reinforcement Learning — mentioned by pjscott

Mon, 17 Apr 2017 23:15:16 GMT

The key problem with the TPU architecture for training is that its on-die buffer space is fairly limited and its memory bandwidth is currently nowhere near that of a GPU. This matters if you've got a lot of intermediate buffers that need to be alive at the same time for backpropagation. Also, there's the less fundamental matter of convenience: while there are some clever ways to train with limited precision gradients, it's not yet as easy as not doing that. One style of training that would be a good fit for the current TPU architecture is some of the recent work on reinforcement learning…

Paper and discussion history. A mention is not an endorsement.

Evolution Strategies as a Scalable Alternative to Reinforcement Learning — mentioned by shpx

Sun, 26 Mar 2017 23:21:38 GMT

> we were able to solve one of the hardest MuJoCo tasks (a 3D humanoid) using 1,440 CPUs across 80 machines in only 10 minutes. As a comparison, in a typical setting 32 A3C workers on one machine would solve this task in about 10 hours. So using 80 times more machines makes you 60 times faster (assuming those are the same machines) "while performing better on 23 games tested, and worse on 28"[0]? [0] The paper for this blog post https://arxiv.org/pdf/1703.03864.pdf Asynchronous advantage actor critic (A3C) https://arxiv.org/pdf/1602.01783.pdf

Paper and discussion history. A mention is not an endorsement.

Evolution Strategies as a Scalable Alternative to Reinforcement Learning — mentioned by taliesinb

Fri, 17 Mar 2017 16:28:22 GMT

I think it's really cool that these kinds of agent models are catching on in the RL world, with this, and OpenAI's recent paper. And with https://arxiv.org/abs/1703.03864 makes me wonder how close we are to seeing deep learning resurrecting good ol' A-life. If I may divert for a moment to wistfully recall an old project... When I was a teen I read Steven Levy's book "Artifical Life". It captured my imagination in a way that the biomorph program in a Blind Watchmaker also had. Ever since then I've played with toy alife models. Some of the attraction is just aesthetic - it's fun to set these…

Paper and discussion history. A mention is not an endorsement.

Evolution Strategies as a Scalable Alternative to Reinforcement Learning — HN submission

Tue, 14 Mar 2017 19:51:18 GMT

Evolution Strategies as a Scalable Alternative to Reinforcement Learning

3 points; 0 discussion replies on HN. Paper and source history. A submission is not an endorsement.