This is the Linux app named Evolution Strategies Starter whose latest release can be downloaded as evolution-strategies-startersourcecode.tar.gz. It can be run online in the free hosting provider OnWorks for workstations.
Download and run online this app named Evolution Strategies Starter with OnWorks for free.
このアプリを実行するには、次の手順に従ってください。
-1。このアプリケーションをPCにダウンロードしました。
--2。ファイルマネージャーhttps://www.onworks.net/myfiles.php?username=XXXXXに必要なユーザー名を入力します。
-3。このアプリケーションをそのようなファイルマネージャにアップロードします。
-4。このWebサイトからOnWorksLinuxオンラインまたはWindowsオンラインエミュレーターまたはMACOSオンラインエミュレーターを起動します。
-5。起動したばかりのOnWorksLinux OSから、必要なユーザー名でファイルマネージャーhttps://www.onworks.net/myfiles.php?username=XXXXXにアクセスします。
-6。アプリケーションをダウンロードし、インストールして実行します。
スクリーンショット：
進化戦略スターター
説明：
evolution-strategies-starter is an archived OpenAI research project that provides a distributed implementation of the algorithm described in the paper “Evolution Strategies as a Scalable Alternative to Reinforcement Learning” by Tim Salimans, Jonathan Ho, Xi Chen, and Ilya Sutskever. The repository demonstrates how to scale Evolution Strategies (ES) for reinforcement learning tasks using a master-worker architecture, where the master node broadcasts parameters to multiple workers, and the workers return performance results after evaluation. This approach allows for efficient parallelization and robustness against worker termination, making it ideal for distributed execution on Amazon EC2 spot instances. The codebase supports building custom AMIs with Packer, integrates with MuJoCo for simulation-based experiments, and includes scripts for launching and managing large-scale runs. While no longer actively maintained, the repository serves as a historical and educational reference.
オプション
- Distributed implementation of OpenAI’s Evolution Strategies algorithm
- Master-worker architecture for scalable parallel computation
- Designed for deployment on Amazon EC2 spot instances
- Includes setup scripts for Packer-based AMI creation and configuration
- Supports MuJoCo environments for physics-based RL experiments
- Reproducible example configurations for humanoid scaling experiments
プログラミング言語
Python、Unixシェル
カテゴリー
This is an application that can also be fetched from https://sourceforge.net/projects/evolution-strat-start.mirror/. It has been hosted in OnWorks in order to be run online in an easiest way from one of our free Operative Systems.