Stars
Type annotations and runtime checking for shape and dtype of JAX/NumPy/PyTorch/etc. arrays. https://docs.kidger.site/jaxtyping/
PaddleSlim is an open-source library for deep model compression and architecture search.
One repository is all that is necessary for Multi-agent Reinforcement Learning (MARL)
Adversarial skill embeddings for training reusable controllers for physically simulated characters.
High throughput synchronous and asynchronous reinforcement learning
Modular Reinforcement Learning (RL) library (implemented in PyTorch, JAX, and NVIDIA Warp) with support for Gymnasium/Gym, NVIDIA Isaac Lab, Brax and other environments
The source code for the blog post The 37 Implementation Details of Proximal Policy Optimization
🦁 A research-friendly codebase for fast experimentation of multi-agent reinforcement learning in JAX
Streamlining reinforcement learning with RLOps. State-of-the-art RL algorithms and tools, with 10x faster training through evolutionary hyperparameter optimization.
Adan: Adaptive Nesterov Momentum Algorithm for Faster Optimizing Deep Models
Official implementation of HARL algorithms based on PyTorch.
Honor of Kings AI Open Environment of Tencent
RL starter files in order to immediately train, visualize and evaluate an agent without writing any line of code
An extension of the PyMARL codebase that includes additional algorithms and environment support
A 3D computer vision development toolkit based on PaddlePaddle. It supports point-cloud object detection, segmentation, and monocular 3D object detection models.
Decision Intelligence Platform for Autonomous Driving simulation.
DRLib：a Concise Deep Reinforcement Learning Library, Integrating HER, PER and D2SR for Almost Off-Policy RL Algorithms.
A parallel framework for population-based multi-agent reinforcement learning.
BenchMARL is a library for benchmarking Multi-Agent Reinforcement Learning (MARL). BenchMARL allows to quickly compare different MARL algorithms, tasks, and models while being systematically ground…
DQN Zoo is a collection of reference implementations of reinforcement learning agents developed at DeepMind based on the Deep Q-Network (DQN) agent.
DSAC-v2; DSAC-T; DASC; Distributional Soft Actor-Critic
This project aims to provide a data and control bridge for the communication between the latest version of Apollo and Carla.
🏛️A research-friendly codebase for fast experimentation of single-agent reinforcement learning in JAX • End-to-End JAX RL
A Massively Parallel Large Scale Self-Play Framework