The Certosa di Pontignano, the course venue, is Sold-Out

Accommodation near the Course Venue

Near to the course venue, the Certosa di Pontignano, there  is the B&B Casa Certosa Via Pontignanello 4 – Castelnuovo Berardenga, Siena (, it is at walking distance from the Certosa di Pontignano.

If you want you can check Terre di Siena (, which is only 7 km from the course venue.

Other Accommodation Options

Useful Information: Transfer, Travel, UNESCO World Heritage Sites & Lifestyle in Siena and Tuscany

1) Transfer

There will be a transfer from Pisa International Airport to Certosa di


  • From Pisa Int. Airport To Course Location (Certosa di Pontignano):
        • departure: 18:00 July 14, 2019
        • arrival: 20:00 July 14, 2019
  • From Course Location (Certosa di Pontignano) To Pisa Int. Airport:
        • departure:  9:00am July 20, 2019
        • arrival: 11:00am July 20, 2019

Please, do not hesitate to call (by phone or via email) Dr. Pasquinuzzi – Certosa di

Pontignano to book your transfer.

Loc. Pontignano, 5 – 53019, Castelnuovo Berardenga (Siena) – Tuscany – Italy

phone: +39-0577-1521104



2) Travel

It follows a list of additional links and information

2.1) Travel Information at the ACDL 2019 web site:

2.2) From Siena Railway Station  to the Certosa di Pontiganno (the

Course venue) there are 15 minutes (about 10Km, that is, about 6 mi),

it costs about 20 Euro by taxi.

2.3) Directions from Siena Train Station to Certosa di Pontignano – Siena,+53100+Siena+SI,+Italia/Certosa+di+Pontignano+-+Siena,+Pontignano,+SI,+Italia/@43.3550219,11.3060271,13z/data=!3m1!4b1!4m14!4m13!1m5!1m1!1s0x132a2dc29c4415cf:0xdae9ad7800ae5970!2m2!1d11.3217065!2d43.3322873!1m5!1m1!1s0x132bd2a49e1d875b:0x4e184663b831d960!2m2!1d11.3597716!2d43.3688812!3e0?hl=en

2.4) From Florence to Siena, there is a direct Train (about 1h17  – 1h28).

2.5) For additional information about the transfer you can ask to

Dr. Pasquinuzzi – Certosa di Pontignano to book your transfer.

Loc. Pontignano, 5 – 53019, Castelnuovo Berardenga (Siena) – Tuscany – Italy

phone: +39-0577-1521104


How to get to Certosa di Pontignano (from Siena city center)

The Certosa di Pontignano is located just a few km from Siena, in the hills of Chianti and Tuscany, famous all over the world.

Once arrived in Siena, the easiest way to catch Certosa di Pontignano, where the Course is going to be held, is by taxi, it will take about 20 minutes. Telephone number of the radio taxi is: +39 (0)577 49222.

There is also a urban Bus from Siena – Piazza Gramsci to Pontignano (bus number 34), but there are only five daily trips. Here you can find the timetable to Pontignano and from Pontignano.

By bus

In Siena (Piazza Gramsci) take number 34 of the bus service (by TIEMME SPA). For schedules and more information, please visit

By taxi

For taxi service, use this phone number: (+39) 0577-49222.

3) The 7 UNESCO World Heritage Sites in Tuscany

  1. Florence, the Cradle of Renaissance: the Core of Tuscany’s Cultural Identity
  2. The White Splendor Pisa’s Piazza dei Miracoli
  3. San Gimignano and its Medieval Towers
  4. Siena, the Beauty
  5. Pienza, the Ideal City for Man
  6. Val d’Orcia: greetings from Tuscany
  7. The Medici Villas and Gardens

4) Lifestyle in Siena and Tuscany

4.1) The Top  Experience in the World is  a Cooking Class and Lunch at a Tuscan Farmhouse with Local Market Tour from Florence, Florence, Italy

4.2) Rent a Bike in Siena


Bicycle tour friends association
Address: via Campaansi 32

Phone: 0577 45159 / Email:

Website – More info:

4.3) Excursions/Visits around Siena

5) Accommodation near the Course Venue

Near to the course venue, the Certosa di Pontignano, there  is the B&B Casa Certosa (, it is at walking distance from the Certosa di Pontignano, or if you want you can check Siena (, which is only 7 km from the course venue.

6) Wine & Food: an encyclopedia wouldn’t be enough …


Simply the best: Brunello, Chianti and Sassicaia “the Super Tuscan”.


Please try tripadvisor:

ACDL 2019 Project on BabyAI Platform

ACDL 2019 Projects on BabyAI

Maxime Chevalier-Boisvert & Giuseppe Nicosia


“I share with many others a dream of learning machines which learn like
babies do, with the help of humans, about how their environment works,
acquiring gradually more complex skills, understanding, and language.
Motivated by this vision, we have developed the BabyAI platform. If you
want to do research on instruction following and/or language grounding,
consider using it: 10^19 synthetic instructions, 19 levels of varying
difficulty. Work done by @MILAMontreal with the help of @Element_AI.”

                                                                            Yoshua Bengio

For students who must pass the ACDL 2019 Course with an exam/project in order to obtain the ECTS points, this year ACDL 2019 has the following project on BabyAI Platform.

Obviously all the participants are invited to work on the project on BabyAI.

BabyAI is a platform for simulating language learning with a human in the loop. This is an ongoing research project based at Mila.

BabyAI: A Platform to Study the Sample Efficiency of Grounded Language Learning

Maxime Chevalier-Boisvert, Dzmitry Bahdanau, Salem Lahlou, Lucas Willems, Chitwan Saharia, Thien Huu Nguyen, Yoshua Bengio

BabyAI is an open-ended grounded language acquisition effort at Mila. The current BabyAI platform was designed to study data-efficiency of existing methods under the assumption that a human provides all teaching signals (i.e. demonstrations, rewards, etc.).

If you have questions on the code or otherwise you can write to Maxime Chevalier-Boisvert ( and Dima Bahdanau (

It is strongly recommended to approach this project with a group!  

At the end of the course, the team members will present the results to the lecturers and the directors.

It follows the list of projects on BabyAI:

  1. To perform experiments on curriculum learning and manually designing curriculums (or automatically sampling which levels to train on based on learning progress). This paper may be inspirational (
  2. To play with unsupervised exploration for representation learning, having agents learn things on their own in the environment without supervision (e.g. how to navigate from room to room). It seems clear that much of what an agent has to learn is not task-specific, but rather understanding the basic mechanics of how it can interact with the world.
  3. Projects on model-based reinforcement learning for BabyAI:  learning a predictive model and using it for planning which action to take, or using optimization algorithms (or stochastic search) to evolve agent models that learn faster.
  4. Hyper-parameter tuning.
  5. Automatic agent architecture search.
  6. Inverse reinforcement learning.