AIConfPaper
← Search

Alberto Castellini

6 accepted papers

2025

Collaborative Instance Object Navigation: Leveraging Uncertainty-Awareness to Minimize Human-Agent Dialogues

Francesco Taioli, Edoardo Zorzi, Gianni Franchi, Alberto Castellini, Alessandro Farinelli, Marco Cristani +1
ICCV 2025poster

Language-driven instance object navigation assumes that a human initiates the task by providing a detailed description of the target to the embodied agent. While this description is crucial for distinguishing the target from other visually similar instances, providing it prior to navigation can be d…

Cited by 0Source ↗PDF ↗Scholar ↗
2025

Learning Logic Specifications for Policy Guidance in POMDPs: an Inductive Logic Programming Approach

Daniele Meli, Alberto Castellini, Alessandro Farinelli
AAAI 2025technical

Partially Observable Markov Decision Processes (POMDPs) are a powerful framework for planning under uncertainty. They allow to model state uncertainty as a belief probability distribution. Approximate solvers based on Monte Carlo sampling show great success to relax the computational demand and perf…

Cited by 8Source ↗PDF ↗Scholar ↗
2024

Mind the Error! Detection and Localization of Instruction Errors in Vision-and-Language Navigation

Francesco Taioli, Stefano Rosa, Alberto Castellini, Lorenzo Natale, Alessio Del Bue, Alessandro Farinelli +2
IROS 2024

Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a series of natural language instructions. All VLN-CE methods in t

Cited by 13Source ↗Scholar ↗
2024

Scalable Safe Policy Improvement for Factored Multi-Agent MDPs

Federico Bianchi, Edoardo Zorzi, Alberto Castellini, Thiago D. Simão, Matthijs T. J. Spaan, Alessandro Farinelli
ICML 2024poster

In this work, we focus on safe policy improvement in multi-agent domains where current state-of-the-art methods cannot be effectively applied because of large state and action spaces. We consider recent results using Monte Carlo Tree Search for Safe Policy Improvement with Baseline Bootstrapping and…

Cited by 2Source ↗PDF ↗Scholar ↗
2023

Scalable Safe Policy Improvement via Monte Carlo Tree Search

Alberto Castellini, Federico Bianchi, Edoardo Zorzi, Thiago D. Simão, Alessandro Farinelli, Matthijs T. J. Spaan
ICML 2023poster

Algorithms for safely improving policies are important to deploy reinforcement learning approaches in real-world scenarios. In this work, we propose an algorithm, called MCTS-SPIBB, that computes safe policy improvement online using a Monte Carlo Tree Search based strategy. We theoretically prove th…

Cited by 10Source ↗PDF ↗Scholar ↗
2021

POMP++: Pomcp-based Active Visual Search in unknown indoor environments

Francesco Giuliari, Alberto Castellini, Riccardo Berra, Alessio Del Bue, Alessandro Farinelli, Marco Cristani +2
IROS 2021poster

In this paper, we focus on the problem of learning online an optimal policy for Active Visual Search (AVS) of objects in unknown indoor environments. We propose POMP++, a planning strategy that introduces a novel formulation on top of the classic Partially Observable Monte Carlo Planning (POMCP) fra…

Cited by 17Source ↗Scholar ↗