A Python Library for Outlier and Anomaly Detection, Integrating Classical and Deep Learning Techniques

CLIPort: What and Where Pathways for Robotic Manipulation

An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)

Fast and simple implementation of RL algorithms, designed to run fully on GPU.

Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.

High-quality single-file implementations of SOTA Offline and Offline-to-Online RL algorithms: AWAC, BC, CQL, DT, EDAC, IQL, SAC-N, TD3+BC, LB-SAC, SPOT, Cal-QL, ReBRAC

High-quality single file implementation of Deep Reinforcement Learning algorithms with research-friendly features (PPO, DQN, C51, DDPG, TD3, SAC, PPG)

Kairos aims to help you save time by automating repetitive tasks on TradingView such as scanning markets for setups, and refreshing alerts as well as creating new ones.

The Unified Machine Learning Framework

[CoRL'22] PlanT: Explainable Planning Transformers via Object-Level Representations

Graph Neural Network Library for PyTorch

PyTorch version of Stable Baselines, reliable implementations of reinforcement learning algorithms.

Machine Learning and Artificial Intelligence for Medicine.

A toolkit for developing and comparing reinforcement learning algorithms.

Macro-Action Generator-Critic (MAGIC) - Learning Macro-actions for online POMDP planning

Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.

A collection of pre-trained RL agents using Stable Baselines3

Tensors and Dynamic neural networks in Python with strong GPU acceleration

Variational autoencoder implemented in tensorflow and pytorch (including inverse autoregressive flow)

This is the pytorch implementation of the paper - Axiomatic Attribution for Deep Networks.

Interacting with Latent Space of AutoEncoder