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

76 pointsby varunagrawalabout 9 years ago

9 comments

mark_elementabout 9 years ago
Previously on HackerNews: <a href="https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11582345" rel="nofollow">https:&#x2F;&#x2F;news.ycombinator.com&#x2F;item?id=11582345</a>
fcholletabout 9 years ago
Two repos to get started building reinforcement learning agents with Gym and Keras:<p><a href="https:&#x2F;&#x2F;github.com&#x2F;sherjilozair&#x2F;dqn" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;sherjilozair&#x2F;dqn</a><p><a href="https:&#x2F;&#x2F;github.com&#x2F;osh&#x2F;kerlym" rel="nofollow">https:&#x2F;&#x2F;github.com&#x2F;osh&#x2F;kerlym</a>
washtabout 9 years ago
This is awesome. All that&#x27;s missing is a self driving car environment ;)
mjs2600about 9 years ago
The focus on improving reinforcement learning is really exciting. It&#x27;s the area of machine learning that seems to have the most untapped potential.
fizzbatterabout 9 years ago
For those more familiar in this scape - would something like this be possible for NLP? Specifically sentence classification (ie, to produce an intent with metadata)?
评论 #11722902 未加载
vagabondvectorabout 9 years ago
kudos for citing Searn, it&#x27;s one of the greatest joint prediction and learning algorithms that started a whole range of useful learning to search approaches.<p>LOLS is even better. all approaches inspired by the reinforcement learning but use the information from already present data to imitate the constructed policy.<p>training neural networks with the approach of LOLS could make so many tasks reachable.<p>one could probably even imitate a komodo 9 algorithm with it.
dharma1about 9 years ago
Would be great to have Unity3D or Unreal Engine integration for games&#x2F;simulations
评论 #11723481 未加载
bodytaingabout 9 years ago
Are there any existing projects based on this, just looking for some examples
udklabout 9 years ago
Does anyone else think the title&#x2F;url is misleading ?<p>Looking at &#x27;Open AI&#x27;, I expected a generic AI related open source project.<p>This project seems to be specifically related to &quot;developing and comparing reinforcement learning (RL) algorithms&quot; .... which looks like a more specific subset.
评论 #11722910 未加载