danijar/dreamerv2

Mastering Atari with Discrete World Models

60
/ 100
Established

This project helps reinforcement learning researchers and practitioners train agents that can master complex tasks, particularly in simulated environments like Atari games or robotic control. You provide the environment's visual observations, and it outputs a highly skilled agent capable of achieving human-level or better performance. It's designed for those developing or evaluating advanced AI agents.

1,012 stars. No commits in the last 6 months. Available on PyPI.

Use this if you need to train a high-performing AI agent for simulated environments by learning directly from pixel inputs.

Not ideal if your primary goal is to deploy an agent in a real-world physical system without significant adaptation, or if you need a simple, interpretable model for basic tasks.

reinforcement-learning game-AI robotics-simulation AI-research agent-training
Stale 6m No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 25 / 25
Community 25 / 25

How are scores calculated?

Stars

1,012

Forks

210

Language

Python

License

MIT

Last pushed

Jan 21, 2023

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danijar/dreamerv2"

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