Search Results - "Berducci, Luigi"

Safe Policy Improvement in Constrained Markov Decision Processes by Berducci, Luigi, Grosu, Radu

“…LNCS 13701 (2022) 360-381; The automatic synthesis of a policy through reinforcement learning (RL) from a given set of formal requirements depends on the…”
Get full text

Learning Adaptive Safety for Multi-Agent Systems by Berducci, Luigi, Yang, Shuo, Mangharam, Rahul, Grosu, Radu

“…Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing…”
Get full text

Scenario-Based Curriculum Generation for Multi-Agent Autonomous Driving by Brunnbauer, Axel, Berducci, Luigi, Priller, Peter, Nickovic, Dejan, Grosu, Radu

“…The automated generation of diverse and complex training scenarios has been an important ingredient in many complex learning tasks. Especially in real-world…”
Get full text

Learning Adaptive Safety for Multi-Agent Systems by Berducci, Luigi, Yang, Shuo, Mangharam, Rahul, Grosu, Radu

“…Ensuring safety in dynamic multi-agent systems is challenging due to limited information about the other agents. Control Barrier Functions (CBFs) are showing…”
Get full text

Enhancing Robot Learning through Learned Human-Attention Feature Maps by Scheuchenstuhl, Daniel, Ulmer, Stefan, Resch, Felix, Berducci, Luigi, Grosu, Radu

“…Robust and efficient learning remains a challenging problem in robotics, in particular with complex visual inputs. Inspired by human attention mechanism, with…”
Get full text

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing by Brunnbauer, Axel, Berducci, Luigi, Brandstatter, Andreas, Lechner, Mathias, Hasani, Ramin, Rus, Daniela, Grosu, Radu

“…World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning…”
Get full text

Hierarchical Potential-based Reward Shaping from Task Specifications by Berducci, Luigi, Aguilar, Edgar A, Ničković, Dejan, Grosu, Radu

“…The automatic synthesis of policies for robotic-control tasks through reinforcement learning relies on a reward signal that simultaneously captures many…”
Get full text

Latent Imagination Facilitates Zero-Shot Transfer in Autonomous Racing by Brunnbauer, Axel, Berducci, Luigi, Brandstätter, Andreas, Lechner, Mathias, Hasani, Ramin, Rus, Daniela, Grosu, Radu

“…World models learn behaviors in a latent imagination space to enhance the sample-efficiency of deep reinforcement learning (RL) algorithms. While learning…”
Get full text