TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

OpenAI Gym: Toolkit for developing, comparing reinforcement learning algorithms

337 pointsby netinstructionsabout 9 years ago

9 comments

jlasabout 9 years ago
Other tools for developing &#x2F; comparing RL algorithms:<p>* Burlap (from Brown-UMBC) <a href="https:&#x2F;&#x2F;github.com&#x2F;jmacglashan&#x2F;burlap" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;jmacglashan&#x2F;burlap</a><p>* RL Glue <a href="http:&#x2F;&#x2F;glue.rl-community.org&#x2F;wiki&#x2F;Main_Page" rel="nofollow">http:&#x2F;&#x2F;glue.rl-community.org&#x2F;wiki&#x2F;Main_Page</a><p>Also looks like some of the challenges come from ALE: <a href="https:&#x2F;&#x2F;github.com&#x2F;mgbellemare&#x2F;Arcade-Learning-Environment" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;mgbellemare&#x2F;Arcade-Learning-Environment</a>
评论 #11583314 未加载
评论 #11584895 未加载
wrsh07about 9 years ago
I don&#x27;t know why it took me this long to realize, but this could be a sort of new-age journal. Published research [on github], reviewed by peers, and reproduced by others. -- gdb@ was that in your mind as you built this?<p>I <i>really</i> hope they gain traction.
评论 #11586002 未加载
Matt3o12_about 9 years ago
Can someone with knowledge in AI explain to me what this framework does compared to others (mainly OS but also proprietary) and if it provides any advances in the field?
评论 #11584506 未加载
评论 #11585618 未加载
wrsh07about 9 years ago
How often will environment versions change? Does a more sophisticated versioning scheme make sense? [like Semantic Versioning?]<p>I don&#x27;t really know what it means to have a backward compatible change in an environment, but you know.
joshmarlowabout 9 years ago
Awesome. I can&#x27;t wait to play with this. I had actually been doing a side project with the same idea (though of course much simpler!). I just got a lot more free time :)
ericjangabout 9 years ago
This is really cool - kind of like Kaggle for RL algorithms!
评论 #11584995 未加载
nxzeroabout 9 years ago
Leaderboards might help grow the community.
评论 #11584390 未加载
评论 #11585490 未加载
patapizzaabout 9 years ago
Awesome. I love these open initiatives to tackle big problems all together (like the bAbI tasks for NLU).
phodoabout 9 years ago
Excellent - thank you.