Bug 2274979 - Review Request: python-torchrl - A PyTorch library for Reinforcement Learning
Summary: Review Request: python-torchrl - A PyTorch library for Reinforcement Learning
Keywords:
Status: NEW
Alias: None
Product: Fedora
Classification: Fedora
Component: Package Review
Version: rawhide
Hardware: Unspecified
OS: Linux
unspecified
medium
Target Milestone: ---
Assignee: Nobody's working on this, feel free to take it
QA Contact: Fedora Extras Quality Assurance
URL:
Whiteboard:
Depends On:
Blocks:
TreeView+ depends on / blocked
 
Reported: 2024-04-14 14:00 UTC by Tom Rix
Modified: 2024-05-21 07:19 UTC (History)
2 users (show)

Fixed In Version:
Doc Type: If docs needed, set a value
Doc Text:
Clone Of:
Environment:
Last Closed:
Type: ---
Embargoed:
trix: fedora-review?


Attachments (Terms of Use)

Description Tom Rix 2024-04-14 14:00:55 UTC
Spec URL: https://trix.fedorapeople.org/python-torchrl.spec
SRPM URL: https://trix.fedorapeople.org/python-torchrl-0.3.1-1.fc41.src.rpm

TorchRL is an open-source Reinforcement Learning (RL) library for PyTorch.                                                                                                       
                                                                                                                                                                                 
It provides PyTorch and python-first, low and high level abstractions for                                                                                                        
RL that are intended to be efficient, modular, documented and properly                                                                                                           
tested. The code is aimed at supporting research in RL. Most of it is                                                                                                            
written in python in a highly modular way, such that researchers can easily                                                                                                      
swap components, transform them or write new ones with little effort.

Reproducible: Always


Note You need to log in before you can comment on or make changes to this bug.