Spinning Up in Deep RL

This developed-and-maintained package is a good approach towards furthering RL development; as the writeups state, the biggest problem in RL is subtle bugs from an implementation which don&#x27;t cause an error but tank learning performance. (+ loggers&#x2F;utils to help debug things)<p>Granted, a lot of RL thought pieces&#x2F;examples on places like Medium.com take an existing RL implementation without many tweaks, run it on a new task, and see what happens. A better RL library might make this workflow more prevalent; hence why it&#x27;s very important for researchers to make their pipelines transparent.

This is awesome and I hope will allow more people to <i>experiment</i> with algorithms, instead of only re-applying OpenAI&#x27;s baselines. Baselines are great, but are very hard (for me, at least) to tinker with.<p>It helps me to understand something new if I can controllably break it. In other words, I progress by predicting the edge-conditions when something shouldn&#x27;t work - and then testing if algorithm indeed experienced expected type of failure. Transparent algorithm implementation is key for this.<p>One thing, which I immediately checked in the spinningup-repo is if it uses TF Eager. And it doesn&#x27;t. @OpenAI what&#x27;s your reasoning for that?

whenever I see high quality submissions I bookmark it and promise myself to come back and spend time learning it.<p>this time...I promise myself its different

Hi! I really appreciate you sharing this with the community. The documents and code look really clear and concise. I do have one question. Is it possible to change the dependency on Mujoco engine to something else (to for e.g. Roboschool)?<p>I don&#x27;t have access to a computer with GPU and I am currently using google colab to do my DL projects. I tried installing Mujoco on colab but unfortunately, the computer id generated seems invalid. Any help is highly appreciated.<p>Thank you!

This looks like an awesome initiative! I think it will be very valuable for people trying to enter the field. I particularly like the clear advice on how to get started doing RL research. Have you considered setting up a forum for the community to share their experiences?

Discovered two small issues in the doc. Where can I send feedback?

is there a Dockerfile with everything set up already?

I thought this was something about roguelikes. :(