jingweiz/pytorch-rl
Deep Reinforcement Learning with pytorch & visdom
This project helps researchers and machine learning engineers develop and experiment with Deep Reinforcement Learning (DRL) agents. It takes configuration parameters for different DRL algorithms and environments, then trains an agent to learn complex behaviors. The output includes trained agent models, real-time performance plots, and detailed training logs, which help users analyze and validate the learning process.
804 stars. No commits in the last 6 months.
Use this if you are a researcher or engineer working on AI that needs to build and train intelligent agents for tasks like game playing or robotic control, and you want to use popular DRL algorithms.
Not ideal if you are looking for a pre-trained, ready-to-deploy AI solution or if you are not comfortable with the concepts and terminology of deep reinforcement learning.
Stars
804
Forks
144
Language
Python
License
MIT
Category
Last pushed
Jul 16, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/jingweiz/pytorch-rl"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related frameworks
DLR-RM/stable-baselines3
PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.
google-deepmind/dm_control
Google DeepMind's software stack for physics-based simulation and Reinforcement Learning...
Denys88/rl_games
RL implementations
pytorch/rl
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
yandexdataschool/Practical_RL
A course in reinforcement learning in the wild