Explore Projects
Discover 47 open source projects
Showing 1-20 of 47 projects
openai/gym
Reinforcement learning toolkit for developing and comparing algorithms.
dennybritz/reinforcement-learning
Reinforcement Learning implementations and exercises for Python developers
AI4Finance-Foundation/FinRL
FinRL is a financial reinforcement learning library that helps developers build AI-driven trading agents.
DLR-RM/stable-baselines3
Reliable PyTorch implementations of reinforcement learning algorithms for AI and robotics applications.
Farama-Foundation/Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities.
vwxyzjn/cleanrl
High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features.
Snouzy/workout-cool
An open-source fitness coaching platform for creating workout plans, tracking progress, and accessing a comprehensive exercise database.
wger-project/wger
A self-hosted fitness, nutrition, and weight tracking app built with Django for personal and community use.
udacity/deep-reinforcement-learning
This is a repository for the Udacity Deep Reinforcement Learning Nanodegree program, focusing on deep reinforcement learning algorithms and techniques.
openai/retro
Retro Games in Gym - A library for integrating classic video games into the OpenAI Gym environment.
datamllab/rlcard
A Python library that provides reinforcement learning algorithms and environments for various card games
Farama-Foundation/HighwayEnv
A minimalist environment for decision-making in autonomous driving powered by reinforcement learning.
unitreerobotics/unitree_rl_gym
RL training framework for Unitree quadruped robots with gym-compatible environments
werner-duvaud/muzero-general
An implementation of the MuZero reinforcement learning algorithm for general-purpose use cases.
DLR-RM/rl-baselines3-zoo
A framework for training Stable Baselines3 reinforcement learning agents with hyperparameter optimization.
Farama-Foundation/Minigrid
A simple and configurable grid world environment for reinforcement learning in Python.
AminHP/gym-anytrading
An OpenAI Gym-based trading environment for developing and testing AI-driven trading algorithms.
openai/roboschool
Open-source robot simulation software for AI development and testing.
Farama-Foundation/ViZDoom
A reinforcement learning environment based on the classic FPS game Doom, useful for AI and ML research.
EMI-Group/evox
Distributed GPU-accelerated framework for evolutionary computation and optimization algorithms.
Stay in the loop
Get weekly updates on trending AI coding tools and projects.