gabrieletiboni

paintnet

PaintNet: Unstructured Multi-Path Learning from 3D Point Clouds for Robotic Spray Painting

dropo

DROPO: Sim-to-Real Transfer with Offline Domain Randomization

doraemon

Domain Randomization via Entropy Maximization

sb3-gym-interface

Interface to stable-baselines3 APIs for training RL policies on gym-registered environments

adr-benchmark

Online vs. Offline Adaptive Domain Randomization Benchmark

exps-launcher

Slurm experiments launcher for python scripts

Incremental-learning-on-CIFAR100

Reproduction of popular methods for class-incremental learning in image recognition and proposal of a new variant.

random-envs

Collection of gym environments with support for domain randomization

Image-classification-on-Caltech101-using-CNNs

Training of a Convolutional Neural Network for image classification on dataset Caltech-101 by using AlexNet structure with both transfer learning and not.

Data-driven-Parkinsons-detection

Shallow machine learning techniques have been analysized and applied for a data-driven diagnosis of Parkinson's desease from patient voice measurements.

Domain-adaptation-on-PACS-dataset

Implementation of DANN, a Domain Adaptation algorithm, on the PACS dataset using AlexNet.

Sentiment-Analysis-on-TripAdvisor-reviews

Binary classification of textual data with traditional ML techniques to predict the mood of a real-world review (positive or negative).

Classification-on-Wine-dataset

Comparison of traditional shallow machine learning techniques for a classification task on the UCI Wine dataset.

senarvi-speech

Tools that I have created for speech recognition and language processing research.

sim2real_rl_robotics_mldl_22

Starting code template for the course project in sim-to-real for reinforcement learning in robotics (machine learning and deep learning 2022 course).

STRICT

Official code for the paper: "A Closer Look at Self-training for Zero-Label Semantic Segmentation" https://arxiv.org/abs/2104.11692

FullStackOpen2021

Open online Full Stack Web Developer course at Aalto University

FullStackOpen2021-part3

Part 3 exercises of Full Stack Web Developer open online course

rf-dropo

Reset-Free DROPO

RL-algorithms-for-Pong-game

Implementation of popular reinforcement learning control algorithms to build an intelligent pong player.

aml22-rl

Starting code for the course project of Advanced Machine Learning in Reinforcement Learning

daai22-rl

Starting code for exam project of Data Analysis and Artificial Intelligence 2022 course @ Politecnico di Torino

learned_optimization

mldl_2024_template

Starting code for course project of MLDL 2024 - 01TXFSM, Polytechnic of Turin.

sim-parameter-estimation

The code accompaniment for the CoRL 2020 paper: A User's Guide to Calibrating Robotics Simulators (https://arxiv.org/abs/2011.08985), from NVIDIA Research Seattle.