Search Results for author: Matteo Leonetti

Found 16 papers, 2 papers with code

Proceedings of the AI-HRI Symposium at AAAI-FSS 2022

no code implementations28 Sep 2022 Zhao Han, Emmanuel Senft, Muneeb I. Ahmad, Shelly Bagchi, Amir Yazdani, Jason R. Wilson, Boyoung Kim, Ruchen Wen, Justin W. Hart, Daniel Hernández García, Matteo Leonetti, Ross Mead, Reuth Mirsky, Ahalya Prabhakar, Megan L. Zimmerman

The Artificial Intelligence (AI) for Human-Robot Interaction (HRI) Symposium has been a successful venue of discussion and collaboration on AI theory and methods aimed at HRI since 2014.

Beyond RMSE: Do machine-learned models of road user interaction produce human-like behavior?

no code implementations22 Jun 2022 Aravinda Ramakrishnan Srinivasan, Yi-Shin Lin, Morris Antonello, Anthony Knittel, Mohamed Hasan, Majd Hawasly, John Redford, Subramanian Ramamoorthy, Matteo Leonetti, Jac Billington, Richard Romano, Gustav Markkula

Even though the models' RMSE value differed, all the models captured the kinematic-dependent merging behavior but struggled at varying degrees to capture the more nuanced courtesy lane change and highway lane change behavior.

Autonomous Vehicles

A Utility Maximization Model of Pedestrian and Driver Interactions

no code implementations21 Oct 2021 Yi-Shin Lin, Aravinda Ramakrishnan Srinivasan, Matteo Leonetti, Jac Billington, Gustav Markkula

Many models account for the traffic flow of road users but few take the details of local interactions into consideration and how they could deteriorate into safety-critical situations.

Meta-Reinforcement Learning for Heuristic Planning

no code implementations6 Jul 2021 Ricardo Luna Gutierrez, Matteo Leonetti

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks.

Meta Reinforcement Learning reinforcement-learning +1

Information-theoretic Task Selection for Meta-Reinforcement Learning

no code implementations NeurIPS 2020 Ricardo Luna Gutierrez, Matteo Leonetti

In Meta-Reinforcement Learning (meta-RL) an agent is trained on a set of tasks to prepare for and learn faster in new, unseen, but related tasks.

Meta Reinforcement Learning reinforcement-learning +1

Curriculum Learning with a Progression Function

no code implementations2 Aug 2020 Andrea Bassich, Francesco Foglino, Matteo Leonetti, Daniel Kudenko

Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learning speed.

reinforcement-learning Reinforcement Learning (RL)

Curriculum Learning for Reinforcement Learning Domains: A Framework and Survey

no code implementations10 Mar 2020 Sanmit Narvekar, Bei Peng, Matteo Leonetti, Jivko Sinapov, Matthew E. Taylor, Peter Stone

Reinforcement learning (RL) is a popular paradigm for addressing sequential decision tasks in which the agent has only limited environmental feedback.

reinforcement-learning Reinforcement Learning (RL) +1

Human-like Planning for Reaching in Cluttered Environments

1 code implementation28 Feb 2020 Mohamed Hasan, Matthew Warburton, Wisdom C. Agboh, Mehmet R. Dogar, Matteo Leonetti, He Wang, Faisal Mushtaq, Mark Mon-Williams, Anthony G. Cohn

From this, we devised a qualitative representation of the task space to abstract the decision making, irrespective of the number of obstacles.

Decision Making

A gray-box approach for curriculum learning

no code implementations17 Jun 2019 Francesco Foglino, Matteo Leonetti, Simone Sagratella, Ruggiero Seccia

Curriculum learning is often employed in deep reinforcement learning to let the agent progress more quickly towards better behaviors.

reinforcement-learning Reinforcement Learning (RL) +1

Curriculum Learning for Cumulative Return Maximization

1 code implementation13 Jun 2019 Francesco Foglino, Christiano Coletto Christakou, Ricardo Luna Gutierrez, Matteo Leonetti

We propose a task sequencing algorithm maximizing the cumulative return, that is, the return obtained by the agent across all the learning episodes.

Combinatorial Optimization Transfer Learning

An Optimization Framework for Task Sequencing in Curriculum Learning

no code implementations31 Jan 2019 Francesco Foglino, Christiano Coletto Christakou, Matteo Leonetti

In reinforcement learning, all previous task sequencing methods have shaped exploration with the objective of reducing the time to reach a given performance level.

reinforcement-learning Reinforcement Learning (RL)

Cannot find the paper you are looking for? You can Submit a new open access paper.