TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

ElegantRL: A Lightweight and Stable Deep Reinforcement Learning Library

26 点作者 yanglet大约 4 年前

2 条评论

yanglet大约 4 年前
Learn to implement deep reinforcement learning algorithms in 24 hours.<p>The ElegantRL library is featured with “elegant” in the following aspects:<p>Lightweight: core codes have less than 1,000 lines, e.g., tutorial.<p>Efficient: the performance is comparable with Ray RLlib.<p>Stable: more stable than Stable Baseline 3.<p>ElegantRL supports state-of-the-art DRL algorithms, including discrete and continuous ones, and provides user-friendly tutorials in Jupyter notebooks.<p>The ElegantRL implements DRL algorithms under the Actor-Critic framework, where an Agent (a.k.a, a DRL algorithm) consists of an Actor network and a Critic network. Due to the completeness and simplicity of code structure, users are able to easily customize their own agents.
sanxiyn大约 4 年前
You may want to delete .DS_Store files from the repository.