kc-ml2/SimpleDreamer
A Simplified Pytorch Version of the Dreamer Algorithm
This project offers a simplified, PyTorch-based implementation of the Dreamer algorithm, a technique used in reinforcement learning. It helps researchers and practitioners train AI agents to efficiently learn complex behaviors in various environments, even with limited interaction data. You provide environmental observations (like images or sensor data), and it outputs an agent capable of performing tasks effectively within that environment.
151 stars. No commits in the last 6 months.
Use this if you are a researcher or practitioner in reinforcement learning looking for a clear, accessible PyTorch implementation of the Dreamer algorithm to understand its mechanics or test new ideas.
Not ideal if you need a high-performance, production-ready implementation of Dreamer, as this version prioritizes readability over speed by using single-step lambda calculation.
Stars
151
Forks
26
Language
Python
License
MIT
Category
Last pushed
Jul 24, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/kc-ml2/SimpleDreamer"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
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...