danijar/dreamer
Dream to Control: Learning Behaviors by Latent Imagination
This project helps machine learning researchers train agents to perform complex tasks by learning from simulated environments. It takes in observations from a simulated world, like a robot trying to walk, and outputs a control policy that dictates how the agent should behave to achieve its goals. It's designed for reinforcement learning scientists and practitioners developing autonomous agents.
584 stars. No commits in the last 6 months. Available on PyPI.
Use this if you are a researcher or engineer looking to efficiently train deep reinforcement learning agents using model-based methods, particularly for control tasks in simulated environments.
Not ideal if you need a reinforcement learning solution for real-world, physical systems without a robust simulation, or if you require an off-the-shelf application rather than a research tool.
Stars
584
Forks
119
Language
Python
License
MIT
Category
Last pushed
Sep 10, 2021
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/danijar/dreamer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Compare
Related frameworks
galilai-group/stable-worldmodel
Reliable, minimal and scalable library for evaluating and conducting world model research
NM512/dreamerv3-torch
Implementation of Dreamer v3 in pytorch.
danijar/dreamerv2
Mastering Atari with Discrete World Models
danijar/dreamerv3
Mastering Diverse Domains through World Models
leofan90/Awesome-World-Models
A comprehensive list of papers for the definition of World Models and using World Models for...