OpenEnv Module 1: From Cartpole to Production-Ready Reinforcement Learning#1
OpenEnv Module 1: From Cartpole to Production-Ready Reinforcement Learning#1ankityadav64194-boop wants to merge 1 commit into
Conversation
|
Hey @ankityadav64194-boop I saw that you worked on the OpenEnv course repo and managed to run the module-1 notebook. I’ve been trying to run it on Google Colab, but I keep getting errors like "ModuleNotFoundError: No module named 'envs'" and issues with loading the echo environment. Did you run it locally or on Colab? And could you share what exact steps/setup worked for you? Would really appreciate any help — I’m kind of stuck on this part |
|
ya, facing the same issue of "ModuleNotFoundError: No module named 'envs'", right now i am using colab extension with my vs code. |
|
@AryanAnand-ux According to the docs of the openenv here we need to do the following install via the notebook pip install git+https://huggingface.co/spaces/openenv/echo_envit, then raises the issue of Collecting git+https://huggingface.co/spaces/openenv/echo_env
Cloning https://huggingface.co/spaces/openenv/echo_env to [/tmp/pip-req-build-4qpmklyr](https://file+.vscode-resource.vscode-cdn.net/tmp/pip-req-build-4qpmklyr)
Running command git clone --filter=blob:none --quiet https://huggingface.co/spaces/openenv/echo_env [/tmp/pip-req-build-4qpmklyr](https://file+.vscode-resource.vscode-cdn.net/tmp/pip-req-build-4qpmklyr)
fatal: could not read Username for 'https://huggingface.co/': No such device or address
error: subprocess-exited-with-errorThen i tried logging into my hugging face account via Which works fine but, does not resolve the issue of the pip install envs, if you find any way round here or solution please let me know. Thank you for your help. |
|
Use this huggingface#2 (comment) |
This module introduces the core concept behind OpenEnv—running reinforcement learning environments as scalable, production-ready microservices.
You will interact with real hosted environments using a simple, universal interface (reset(), step(), state()), and experience how modern RL systems move beyond local experimentation into cloud-based, distributed infrastructure.