prolearner

Riccardo Grazzi's repositories

procedural-planet

a 3D procedural Planet in THREEJS and WebGl

Language:JavaScriptMIT47 6 2

hyper-representation

This is the official repo for the experiments in the paper "Bilevel Programming for Hyperparameter Optimization and Meta-Learning"

Language:Python31 50

LearningToCompareTF

implementation of the learning to compare article using tensorflow

Language:Python11 3 1

onlineLTL

python implementation of online learning to learn non-smooth algorithms

Language:Python3 40

nonsmooth_implicit_diff

Code for the paper Nonsmooth Implicit Differentiation: Deterministic and Stochastic Convergence Rates by Riccardo Grazzi, Massimiliano Pontil and Saverio Salzo (ICML 2024).

Language:Jupyter NotebookMIT100

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

Language:PythonMIT020

certifiable-distributional-robustness

Certifying Some Distributional Robustness with Principled Adversarial Training (https://arxiv.org/abs/1710.10571)

Language:PythonApache-2.0020

gluon-ts

Probabilistic time series modeling in Python

Language:PythonApache-2.0010

gym

A toolkit for developing and comparing reinforcement learning algorithms.

Language:PythonNOASSERTION030

koopmanAE

Consistent Koopman Autoencoders

Language:Python000

maml_rl

Code for RL experiments in "Model-Agnostic Meta-Learning for Fast Adaptation of Deep Networks"

Language:PythonNOASSERTION030

movielens

4 different recommendation engines for the MovieLens dataset.

Language:Jupyter NotebookMIT020

neuraloperator

Learning in infinite dimension with neural operators.

MIT000

PokemonGo-Map

Live visualization of all the pokemon in your area... and more!

Language:PythonAGPL-3.0020

PokemonGo-Map-1

🌏 Live visualization of all the pokemon in your area... and more!

Language:PythonAGPL-3.0010

PyTorch implementation of Advantage Actor Critic (A2C), Proximal Policy Optimization (PPO) and Scalable trust-region method for deep reinforcement learning using Kronecker-factored approximation (ACKTR).

Language:PythonMIT030