godka/Pensieve-PPO

The simplest implementation of Pensieve (SIGCOMM' 17) via state-of-the-art RL algorithms, including PPO, DQN, SAC, and support for both TensorFlow and PyTorch.

46
/ 100
Emerging

This project helps video streaming engineers and researchers develop and test adaptive video streaming algorithms. It takes network conditions and video quality metrics as input to produce optimized streaming policies that improve the viewer's Quality of Experience (QoE). This is for professionals working on improving how video content is delivered to end-users.

No commits in the last 6 months.

Use this if you are a network researcher or video platform engineer looking to train and evaluate neural adaptive video streaming systems, especially using Proximal Policy Optimization (PPO).

Not ideal if you are a consumer looking for an off-the-shelf video player or if you are not familiar with reinforcement learning concepts and video streaming optimization.

video-streaming network-optimization quality-of-experience adaptive-bitrate reinforcement-learning
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 9 / 25
Maturity 16 / 25
Community 21 / 25

How are scores calculated?

Stars

87

Forks

41

Language

DIGITAL Command Language

License

BSD-2-Clause

Last pushed

Jan 18, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/godka/Pensieve-PPO"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.