Welcome to the Knowledge, Reasoning and Learning Research Group

The Knowledge, Reasoning and Learning Group at the University “Sapienza” of Rome is a dynamic research group of faculty, PhD and master students inside the Ro.Co.Co. Lab. It is led by prof. Roberto Capobianco and current emphases of research includes robot learning, knowledge acquisition and learning, reinforcement learning and explainable artificial intelligence. KRL members are also involved on works in collaboration with other research areas like chemistry, exoplanet exploration and industrial robot application.

We are looking for passionate new PhD students, Postdocs, and Master students to join the team (more info) !

We are grateful for funding from:

Latest News

7. October 2021

We are happy to share that we have four papers accepted at AIxIA 2021!!! Congratulation to all the students and collaborators! They are: "Exploration-Intensive Distractors: Two Environment Proposals and a Benchmarking" by Jim Martin Catacora Ocaña, Roberto Capobianco and Daniele Nardi; "Detection Accuracy for Evaluating Compositional Explanations of Units" by Sayo M. Makinwa, Biagio La Rosa and Roberto Capobianco; "A Discussion about Explainable Inference on Sequential Data via Memory-Tracking" by Biagio La Rosa, Roberto Capobianco, and Daniele Nardi; and "Tafl-ES: Exploring Evolution Strategies for Asymmetrical Board Games" by Roberto Gallotta and Roberto Capobianco. The link will be available online as soon as possible.

19. August 2021

We are happy to announce that our paper "Agent-Based Markov Modeling for Improved COVID-19 Mitigation Policies" has been published in JAIR (Journal of Artificial Intelligence Research). Joint work between Roberto Capobianco, Varun Raj Kompella, James Ault, Guni Sharon, Stacy Jong, Spencer Fox, Lauren Meyers, Peter Wurman and Peter Stone. In this paper, we study how reinforcement learning and Bayesian inference can be used to optimize mitigation policies that minimize economic impact without overwhelming hospital capacity. For more details, check out the manuscript here.

28. June 2021

Our paper "Learning Transferable Policies for Autonomous Planetary Landing via Deep Reinforcement Learning", submitted to ascend aiaa 2021 has been accepted! Joint work between Giulia Ciabatti, Shreyansh Daftry and Roberto Capobianco. Link to the paper is coming soon!

26. April 2021

Our paper "Autonomous Planetary Landing via Deep Reinforcement Learning and Transfer Learning" has been accepted for publication at CVPR 2021, AI for Space.

3. March 2021

Check out the new blog post from Dr. Peter Stone about the Pandemic Simulator on the site of Sony AI. It describes the ideas behind our recent papers “Multiagent Epidemiologic Inference through Realtime Contact Tracing” and “Reinforcement Learning for Optimization of COVID-19 Mitigation Policies”!

... see all News