sudo-michael

rsl_rl

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

rtgym

Easily implement custom Gymnasium environments for real-time applications

FISOR

[ICLR 2024] The official implementation of "Safe Offline Reinforcement Learning with Feasibility-Guided Diffusion Model"

CrossQ

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

HILP

Foundation Policies with Hilbert Representations (ICML 2024)

purejaxrl

Really Fast End-to-End Jax RL Implementations

jax_trainer

Lightning-like training API for JAX with Flax

drift

Dead Reckoning In Field Time: Symmetry-Preserving State Estimation Library for Various Robotic Platforms

parameterfree

Parameter-Free Optimizers for Pytorch

ABS

dittogym

Code for "DittoGym: Learning to Control Soft Shape-Shifting Robots" by Suning Huang, Boyuan Chen, Huazhe Xu, and Vincent Sitzmann.

ml-engineering

Machine Learning Engineering Open Book

Safe-Deep-Reinforcement-Learning

VeriTree

rpo

Official implementation for the NeurIPS 2023 paper: "Reduced Policy Optimization for Continuous Control with Hard Constraints"

mticl

mbrcsl

levanter

Legible, Scalable, Reproducible Foundation Models with Named Tensors and Jax

EmerNeRF

PyTorch Implementation of EmerNeRF: Emergent Spatial-Temporal Scene Decomposition via Self-Supervision

Automatic-Parking

Python implementation of an automatic parallel parking system in a virtual environment, including path planning, path tracking, and parallel parking

jaxrl_m

Skeleton for scalable and flexible Jax RL implementations

Reachability_Constrained_RL

Official open-source implementation of ICML 2022 paper: Reachability Constrainted Reinforcement Learning.

rtui

TUI tool for ROS

proactive_interventions

Codebase for NeurIPS 2022 paper, "When to Ask for Help: Proactive Interventions in Autonomous Reinforcement Learning"

sfuthesis

Cleaned-up LaTeX classes and templates for SFU grad students

fantasque-sans

A font family with a great monospaced variant for programmers.

safe-rl-robustness

Code for "On the Robustness of Safe Reinforcement Learning under Observational Perturbations" (ICLR 2023)

jax-cpo

Implementation of Constrained Policy Optimization with JAX

decqn

effective-horizon

Code and data for the paper "Bridging RL Theory and Practice with the Effective Horizon"