💡 [REQUEST] - Port TorchRL Pendulum
tutorial from pytorch.org/rl to pytorch.org/tutorials
#2352
Labels
Pendulum
tutorial from pytorch.org/rl to pytorch.org/tutorials
#2352
Uh oh!
There was an error while loading. Please reload this page.
🚀 Descirbe the improvement or the new tutorial
For historical reasons, TorchRL privately hosts a bunch of tutorials.
We'd like to bring the most significant ones to pytorch tutorials for more visibility.
Here is the tutorial.
Environments (or simulators) are a core part of many RL algorithms. The OpenAI Gym API has had a great success in the past years and paved the way for RL researchers to quickly test ideas with an easy-to-use tool.
As a PyTorch-first library, torchrl aims at being (1) oblivious to the simulator (gym or other), (2) rely on pytorch for anything we can in the simulation process, (3) a good integration within the library and (4) a coverage of many different types of environments (simulators, real-life hardware, model-based, RLHF etc). For these reasons, TorchRL propose its own class of environments. We have a dedicated tutorial that covers their design and usage: you can help us port it where it belongs!
Steps:
Existing tutorials on this topic
No response
Additional context
The tutorial should not require extra dependencies beyond those already present in requirements.txt
cc @nairbv @sekyondaMeta @svekars @carljparker @NicolasHug @kit1980 @subramen @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10 @ZailiWang @ZhaoqiongZ @leslie-fang-intel @Xia-Weiwen @sekahler2 @CaoE @zhuhaozhe @Valentine233
The text was updated successfully, but these errors were encountered: