sudo-michael

PythonRobotics

Python sample codes for robotics algorithms.

optuna

A hyperparameter optimization framework

sioyek

Sioyek is a PDF viewer with a focus on textbooks and research papers

HEBO

Bayesian optimisation & Reinforcement Learning library developped by Huawei Noah's Ark Lab

dm-haiku

JAX-based neural network library

image-to-latex

Convert images of LaTex math equations into LaTex code.

ml-pen-and-paper-exercises

Pen and paper exercises in machine learning

awesome-jax

JAX - A curated list of resources https://github.com/google/jax

autodidact

A pedagogical implementation of Autograd

chex

distrax

Safe-Reinforcement-Learning-Baselines

The repository is for safe reinforcement learning baselines.

Safe-Policy-Optimization

NeurIPS 2023: Safe Policy Optimization: A benchmark repository for safe reinforcement learning algorithms

TD3_BC

Author's PyTorch implementation of TD3+BC, a simple variant of TD3 for offline RL

gym-line-follower

Line follower robot simulator environment for Open AI Gym.

rl_with_resets

JAX implementation of deep RL agents with resets from the paper "The Primacy Bias in Deep Reinforcement Learning"

Conjugate-Gradient

Painless conjugate gradient notebooks

safe-mbrl

Safe Model-based Reinforcement Learning with Robust Cross-Entropy Method

Bullet-Safety-Gym

An open-source framework to benchmark and assess safety specifications of Reinforcement Learning problems.

cvpo-safe-rl

Code for "Constrained Variational Policy Optimization for Safe Reinforcement Learning" (ICML 2022)

Dropout-Q-Functions-for-Doubly-Efficient-Reinforcement-Learning

Source files to replicate experiments in my ICLR 2022 paper.

la-mbda

LAMBDA is a model-based reinforcement learning agent that uses Bayesian world models for safe policy optimization

reachability-based_trajectory_safeguard

We use reachability to ensure the safety of a decision agent acting on a dynamic system in real-time. We compute the Forward Reachable Set offline and use it online to adjust any potentially unsafe decisions that cause a collision with an obstacle.

safety_rl

LeaveNoTrace

Leave No Trace is an algorithm for safe reinforcement learning.

HJxB

Continuous-Time/State/Action Fitted Value Iteration via Hamilton-Jacobi-Bellman (HJB)

rl_with_jax

clear single-file JAX implementations of common RL algorithms

ISSA

Code for paper "Model-free Safe Control for Zero-Violation Reinforcement Learning" at Conference on Robot Learning (CoRL) 2021.

natural-policy-gradient-reinforcement-learning

code for Understanding the Effects of Second-Order Approximations in Natural Policy Gradient Reinforcement Learning

naturalgradient

code for blog post https://gebob19.github.io/natural-gradient/