lucidrains/streaming-deep-rl

Explorations into the proposed Streaming Deep Reinforcement Learning, from University of Alberta

58
/ 100
Established

This project explores and implements 'Streaming Deep Reinforcement Learning' (SDRL), a new approach to training AI agents. It takes in real-time state observations and rewards from an environment, and outputs optimal actions for the agent to take. This is for AI researchers and practitioners who develop and train intelligent agents for various tasks.

Available on PyPI.

Use this if you are a researcher or advanced practitioner interested in experimenting with and applying cutting-edge streaming reinforcement learning algorithms, particularly those based on actor-critic and Q-learning methods.

Not ideal if you are looking for a plug-and-play solution for general reinforcement learning tasks without needing to understand the underlying algorithmic details or if you're not comfortable with Python development.

reinforcement-learning AI-research agent-training machine-learning-algorithms deep-learning
Maintenance 13 / 25
Adoption 13 / 25
Maturity 25 / 25
Community 7 / 25

How are scores calculated?

Stars

24

Forks

2

Language

Python

License

MIT

Last pushed

Mar 25, 2026

Monthly downloads

804

Commits (30d)

0

Dependencies

7

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/lucidrains/streaming-deep-rl"

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