amarildolikmeta Goto Github PK

alpha-zero-general

A clean implementation based on AlphaZero for any game in any framework + tutorial + Othello/Gobang/TicTacToe/Connect4

alphazero_singleplayer

Single player Alpha Zero implementation

aml_project

awt2017

AWT course project. A crowdsorcing web appilcation, where masters can publish jobs and workers can subscribe and complete the jobs. Built with a model driven approach.

bayesianqlearning

implementation of Bayesian Q Learning RL Algorithm

briscola

Project of Mobile Development class. A native Android implementation of the classic italian Card game

como-center-prediction

A data pipeline used to build a predictive model on the number of people visting the center of the city of Como, Northern Italy, based on data collected by sensors in the city center and weather data

disertation

Disertation of my Master's Thesis : Driving Exploration Trhough Particle Q Distributions

ewrl2022

Website for the European Workshop on Reinforcement Learning 2022

irl_real_life

m2l_poster

Poster and Presentation for 'Handling Non-Stationary Experts inInverse Reinforcement Learning' presented in M2L 2020

models

Models and examples built with TensorFlow

oac-explore

Code accompanying the paper "Better Exploration with Optimistic Actor Critic" (NeurIPS 2019)

prl_2021_open_loop_planning_f1_strategy

reccomender-system

Reccomender systems course project. Contains Collaborative User based, Item based, Content based reccomenders

small-mbrl

torch_workers_gpu

wac_explore

Code reproducing the results of the paper Wasserstein Actor-Critic:Directed Exploration via Optimism for Continuous-Actions Control

wasserstein_actor_critic

Code for the paper "Wasserstein Actor-Critic: Directed Exploration via Optimism for Continuous-Actions Control"

weighteddqn