Download your Spotify playlists and songs along with album art and metadata (from YouTube if a match is found).

Large-scale uncertainty benchmark in deep learning.

Extension of the Dreamer reinforcement learning agent to goal-conditioned robotic environments.

Goal-Conditioned Reinforcement Learning with JAX

Sparse Particle Tree POMDP Solvers

Code for the ICML 2020 publication "Information Particle Filter Tree: An Online Algorithm for POMDPs with Belief-Based Rewards on Continuous Domains"

Online solver based on Monte Carlo tree search for POMDPs with continuous state, action, and observation spaces.

A framework to build and solve POMDP problems. Documentation: https://h2r.github.io/pomdp-py/

Implementation of Partially Observable Monte Carlo Planning Algorithm

This repo contains a simple implementation of batch Gaussian Mixture Regression (GMR) in PyTorch. The main motivation behind this implementation is to enable parallel GMR for multiple GMMs.

Launching and monitoring Slurm experiments in Python

The purpose of this repo is to make it easy to get started with JAX, Flax, and Haiku. It contains my "Machine Learning with JAX" series of tutorials (YouTube videos and Jupyter Notebooks) as well a…

Official code release for "CrossQ: Batch Normalization in Deep Reinforcement Learning for Greater Sample Efficiency and Simplicity"

world modeling challenge for humanoid robots

Long-Term Evolution Project of Reinforcement Learning

Code for "On Uncertainty in Deep State Space Models for Model-Based Reinforcement Learning" (TMLR, 2022)

Official implementation of "Recurrent Networks, Hidden States and Beliefs in Partially Observable Environments"

PyTorch implementation of AVF

Meta-RL Model-Based Algorithm

SBX: Stable Baselines Jax (SB3 + Jax) RL algorithms

Fast and reliable distributed systems in Python

The Mighty cRL library you've been looking for! 💪

Perception Matters: Enhancing Embodied AI with Uncertainty-Aware Semantic Segmentation. Project Website: http://semantic-search.cs.uni-freiburg.de

Official implementation of the Informed Dreamer algorithm, based on DreamerV3

This repo contains the code for 1D tokenizer and generator