instadeepai/sebulba
🪐 The Sebulba architecture to scale reinforcement learning on Cloud TPUs in JAX
Sebulba helps machine learning researchers rapidly train reinforcement learning (RL) agents. It takes in environment observations and outputs optimized agent parameters, allowing researchers to explore and improve AI agent behavior. This system is designed for machine learning researchers working on complex RL problems, especially those involving game environments or simulations.
No commits in the last 6 months.
Use this if you are a researcher needing to scale up your reinforcement learning experiments efficiently, particularly when working with powerful hardware like Cloud TPUs.
Not ideal if you are a beginner looking for an easy-to-use off-the-shelf RL solution or if you don't have access to distributed computing resources.
Stars
61
Forks
5
Language
Python
License
Apache-2.0
Category
Last pushed
Oct 23, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/instadeepai/sebulba"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
nschaetti/EchoTorch
A Python toolkit for Reservoir Computing and Echo State Network experimentation based on...
metaopt/torchopt
TorchOpt is an efficient library for differentiable optimization built upon PyTorch.
opthub-org/pytorch-bsf
PyTorch implementation of Bezier simplex fitting
gpauloski/kfac-pytorch
Distributed K-FAC preconditioner for PyTorch
pytorch/xla
Enabling PyTorch on XLA Devices (e.g. Google TPU)