uber-research/atari-model-zoo

A binary release of trained deep reinforcement learning models trained in the Atari machine learning benchmark, and a software release that enables easy visualization and analysis of models, and comparison across training algorithms.

45
/ 100
Emerging

This project offers a collection of pre-trained deep reinforcement learning (RL) models that have learned to play Atari games. It provides tools to easily analyze, visualize, and compare how these models make decisions and perform. Researchers studying artificial intelligence and machine learning can use this to better understand and develop new RL agents.

202 stars. No commits in the last 6 months.

Use this if you are a machine learning researcher who wants to examine and understand the behavior of existing deep reinforcement learning agents, without having to train them yourself.

Not ideal if you are looking to train new reinforcement learning models from scratch or develop game-playing agents for non-Atari environments.

reinforcement-learning-research ai-agent-analysis deep-learning-visualization atari-benchmarking model-comparison
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

202

Forks

34

Language

Jupyter Notebook

License

Last pushed

May 25, 2020

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/uber-research/atari-model-zoo"

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