Stars
A playbook for systematically maximizing the performance of deep learning models.
Files from the published Alpha Star paper by DeepMind
RevIN: Reversible Instance Normalization For Accurate Time-series Forecasting Against Distribution Shift
Motion imitation with deep reinforcement learning.
OpenAI Baselines: high-quality implementations of reinforcement learning algorithms
Implementations of basic RL algorithms with minimal lines of codes! (pytorch based)
Simple, readable, yet full-featured implementation of PPO in Pytorch
Tutorials for reinforcement learning in PyTorch and Gym by implementing a few of the popular algorithms. [IN PROGRESS]
IntroductionConsider a data communication network that must route data packets (email, MP3 files, or videofiles, for example). Such a network consists of routers connected by physical cables or lin…
A large-scale benchmark and learning environment.
A customisable 3D platform for agent-based AI research
robosuite: A Modular Simulation Framework and Benchmark for Robot Learning
Optax is a gradient processing and optimization library for JAX.
SecLists is the security tester's companion. It's a collection of multiple types of lists used during security assessments, collected in one place. List types include usernames, passwords, URLs, se…
Serve, optimize and scale PyTorch models in production
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
Flax is a neural network library for JAX that is designed for flexibility.
Reimplementation of World-Models (Ha and Schmidhuber 2018) in pytorch
Collection of reinforcement learning algorithms
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
A collection of resources regarding the interplay between differential equations, deep learning, dynamical systems, control and numerical methods.
A PyTorch library entirely dedicated to neural differential equations, implicit models and related numerical methods
Differentiable ODE solvers with full GPU support and O(1)-memory backpropagation.
FastAPI framework, high performance, easy to learn, fast to code, ready for production
Hydra is a framework for elegantly configuring complex applications
A scikit-learn compatible neural network library that wraps PyTorch