alexanderdurr

alpha-zero-boosted

A "build to learn" Alpha Zero implementation using Gradient Boosted Decision Trees (LightGBM)

AlphaZero_Connect4

PyTorch implementation of AlphaZero Connect from scratch (with results)

autolab_core

Core utilities for Berkeley AutoLab.

baselines-results

Chapter16-Robot-Learning-in-Simulation

Chapter 16 Robot Learning in Simulation in book Deep Reinforcement Learning: example of Sawyer robot learning to reach the target with paralleled Soft Actor-Critic (SAC) algorithm, using PyRep for Sawyer robot simulation and game building. The environment is wrapped into OpenAI Gym format.

cmake

CMake lesson material.

conference_call_for_paper

2019-2020 International Conferences in Artificial Intelligence, Machine Learning, Computer Vision, Data Mining, Natural Language Processing and Robotics

e-maml

E-MAML, and RL-MAML baseline implemented in Tensorflow v1

FrankaEmikaPandaDynModel

Dynamic model of the Franka Emika Panda robot

Freenove_Ultimate_Starter_Kit_for_Raspberry_Pi

Apply to FNK0020

goalgail

accompanying code for neurips submission "Goal-conditioned Imitation Learning"

hpc-python

Python in High Performance Computing

jupyter

Course material on Jupyter Notebooks and JupyterLab.

manim

Animation engine for explanatory math videos

manuals

Diverse operation manuals for CodeRefinery workshops and lesson design.

minerl

MineRL Competition for Sample Efficient Reinforcement Learning - Python Package

mvp_grasp

Multi-Viewpoint Picking (ICRA 2019)

NRLPapers

Must-read papers on network representation learning (NRL) / network embedding (NE)

RaspTank

Python Library for communicating with the Adeept RaspTank

rasptank-ros

ROS package for the RaspTank robot from Adeept.

reinforcement-learning

Implementation of Reinforcement Learning Algorithms. Python, OpenAI Gym, Tensorflow. Exercises and Solutions to accompany Sutton's Book and David Silver's course.

reproducible-research

Lesson on reproducible research.

rlbench-documentation

Deep Learning For Robot Agents On RLBench -- Work In Progress

ros_tank

ROS version of tank_robot, with urdf/rviz, gmapping w laser_scan_matcher

rosdyn

The goal of the project ROSdyn is to realize a ROS-based package that implement a fully automated procedure able to calibrate the robot dynamics model. The use of ROS ecosystem enable the standardization of several steps of the procedure, such as the messages exchanged between nodes. A further step towards standardization is represented by the use of ROS-I robot drivers that allow a standard access to all the robot information enabling the dynamics model calibration on commercial IR.

td3_her_rlbench_reacher

A implementation for soving reach target task based on TD3 with HER using PaddlePaddle.

templates

Lund University templates for documents and projects.

testing

Lesson on automated testing.

tuxedo-fan-control

This is an adaption of a tuxedo fan control so it runs and works for a Lambda Labs Tensorbook. The TUXEDO Fan Control is a Application and Daemon for controlling the fans of CPU and GPU of your TUXEDO Notebook device.

WASP-AS1-Assignment1