Lists (1)
Stars
PyTorch implementation of the U-Net for image semantic segmentation with high quality images
Deep universal probabilistic programming with Python and PyTorch
A highly efficient implementation of Gaussian Processes in PyTorch
Learnable latent embeddings for joint behavioral and neural analysis - Official implementation of CEBRA
Contrib package for Stable-Baselines3 - Experimental reinforcement learning (RL) code
Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions' [Liu+, ECCV2018]
NeurIPS 2023: Safety-Gymnasium: A Unified Safe Reinforcement Learning Benchmark
Disentanglement library for PyTorch
Unofficial implementation of the Dreamer 4 world model in PyTorch.
Lightweight multi-agent gridworld Gym environment
DMControl Generalization Benchmark
A Simplified Pytorch Version of the Dreamer Algorithm
Simplest and Cleanest DreamerV3 implementation out there
[NeurIPS 2019] Code for the paper "Learning to Control Self-Assembling Morphologies: A Study of Generalization via Modularity"
Deep active inference agents using Monte-Carlo methods
[ICLR 2025] Robust Gymnasium: A Unified Modular Benchmark for Robust Reinforcement Learning.
This repository contains code for applying Riemannian geometry in machine learning.
Implementation of 'RL^2: Fast Reinforcement Learning via Slow Reinforcement Learning'
The Controllable Agent project trains RL Agents able to optimize any reward function specified in real time, without any further learning or fine-tuning. Training is reward-free and based on the Fo…
Fast and flexible multi-agent gridworld reinforcement learning environments.
CPAB Transformations: finite-dimensional spaces of simple, fast, and highly-expressive diffeomorphisms derived from parametric, continuously-defined, velocity fields in Numpy, Tensorflow and Pytorch
Learning Off-Policy with Online Planning [CoRL 2021 Best Paper Finalist]
[ICML 2023] Pre-train world model-based agents with different unsupervised strategies, fine-tune the agent's components selectively, and use planning (Dyna-MPC) during fine-tuning.
Repository for "Quality-Diversity Actor-Critic: Learning High-Performing and Diverse Behaviors via Value and Successor Features Critics" (ICML 2024).
Implementation of Diversity Is All You Need (DIAYN) on top of Stable Baselines 3.