AIConfPaper
← Search

Leandro Soriano Marcolino

5 accepted papers

2025

Multi Objective Quantile Based Reinforcement Learning for Modern Urban Planning

Lukasz Pelcner, Leandro Soriano Marcolino, Matheus Aparecido do Carmo Alves, Paula A. Harrison, Peter M. Atkinson
IJCAI 2025

We present a novel Multi-Agent Reinforcement Learning approach to understand and improve policy development by land-shaping agents, such as governments and institutional bodies. We derive the underlying policy decisions by analyzing the land and developing an intelligent system that proposes optimal

Cited by 0Source ↗PDF ↗Scholar ↗
2024

Reward Certification for Policy Smoothed Reinforcement Learning

Ronghui Mu, Leandro Soriano Marcolino, Yanghao Zhang, Tianle Zhang, Xiaowei Huang, Wenjie Ruan
AAAI 2024technical

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks. Recent studies have introduced ``smoothed policies" to enhance its robustness. Yet, it is still challenging to establish a provable guarantee to certify the bound of i…

Cited by 5Source ↗PDF ↗code ↗Scholar ↗
2023

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning

Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Gaojie Jin, Qiang Ni
AAAI 2023technical

Cooperative multi-agent reinforcement learning (c-MARL) is widely applied in safety-critical scenarios, thus the analysis of robustness for c-MARL models is profoundly important. However, robustness certification for c-MARLs has not yet been explored in the community. In this paper, we propose a nov…

Cited by 15Source ↗PDF ↗code ↗Scholar ↗
2023

Information-guided Planning: An Online Approach for Partially Observable Problems

Matheus Aparecido Do Carmo Alves, Amokh Varma, Yehia Elkhatib, Leandro Soriano Marcolino
NeurIPS 2023poster

This paper presents IB-POMCP, a novel algorithm for online planning under partial observability. Our approach enhances the decision-making process by using estimations of the world belief's entropy to guide a tree search process and surpass the limitations of planning in scenarios with sparse reward…

Cited by 2Source ↗PDF ↗code ↗Scholar ↗
2020

Straight to the Point: Fast-Forwarding Videos via Reinforcement Learning Using Textual Data

Washington Ramos, Michel Silva, Edson Araujo, Leandro Soriano Marcolino, Erickson Nascimento
CVPR 2020poster

The rapid increase in the amount of published visual data and the limited time of users bring the demand for processing untrimmed videos to produce shorter versions that convey the same information. Despite the remarkable progress that has been made by summarization methods, most of them can only se…

Cited by 7PDF ↗code ↗Scholar ↗