RL
[ICLR25 Oral] RL framework for manipulation of diverse shapes and deformable objects
SERL: A Software Suite for Sample-Efficient Robotic Reinforcement Learning
An elegant PyTorch deep reinforcement learning library.
Modularized Implementation of Deep RL Algorithms in PyTorch
Pytorch Implementation of DQN / DDQN / Prioritized replay/ noisy networks/ distributional values/ Rainbow/ hierarchical RL
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning.
An offline deep reinforcement learning library
An Open Source package that allows video game creators, AI researchers and hobbyists the opportunity to learn complex behaviors for their Non Player Characters or agents
A curated list of awesome model based RL resources (continually updated)
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, Brax and other environments
A PyTorch library for all things Reinforcement Learning (RL) for Combinatorial Optimization (CO)
LeanRL is a fork of CleanRL, where selected PyTorch scripts optimized for performance using compile and cudagraphs.
PyTorch implementation of Soft-Actor-Critic and Prioritized Experience Replay (PER) + Emphasizing Recent Experience (ERE) + Munchausen RL + D2RL and parallel Environments.
pytorch-implementation of Dreamer (Model-based Image RL Algorithm)
Code for Reinforcement Learning from Vision Language Foundation Model Feedback
A Repository with C++ implementations of Reinforcement Learning Algorithms (Pytorch)
Continual RL with wold models (Collas 2023)
Using Deep Deterministic Policy Gradient (DDPG) to solve the 20-agent Unity Reacher problem.
Deep reinforcement learning GPU libraries for NVIDIA Jetson TX1/TX2 with PyTorch, OpenAI Gym, and Gazebo robotics simulator.
Repo for the Deep Reinforcement Learning Nanodegree program
Python Implementation of Reinforcement Learning: An Introduction
PyTorch implementations of deep reinforcement learning algorithms and environments
DrQ-v2: Improved Data-Augmented Reinforcement Learning
Mastering Diverse Domains through World Models