Reward Certification for Policy Smoothed Reinforcement Learning

no code implementations • 11 Dec 2023 • Ronghui Mu, Leandro Soriano Marcolino, Tianle Zhang, Yanghao Zhang, Xiaowei Huang, Wenjie Ruan

Reinforcement Learning (RL) has achieved remarkable success in safety-critical areas, but it can be weakened by adversarial attacks.

reinforcement-learning Reinforcement Learning (RL)

Certified Policy Smoothing for Cooperative Multi-Agent Reinforcement Learning

1 code implementation • 22 Dec 2022 • Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Gaojie Jin, Qiang Ni

The experimental results show that our method produces meaningful guaranteed robustness for all models and environments.

Multi-agent Reinforcement Learning reinforcement-learning +1

Semantic Segmentation under Adverse Conditions: A Weather and Nighttime-aware Synthetic Data-based Approach

1 code implementation • 11 Oct 2022 • Abdulrahman Kerim, Felipe Chamone, Washington Ramos, Leandro Soriano Marcolino, Erickson R. Nascimento, Richard Jiang

Recent semantic segmentation models perform well under standard weather conditions and sufficient illumination but struggle with adverse weather conditions and nighttime.

Domain Adaptation Multi-Task Learning +2

Leveraging Synthetic Data to Learn Video Stabilization Under Adverse Conditions

1 code implementation • 26 Aug 2022 • Abdulrahman Kerim, Washington L. S. Ramos, Leandro Soriano Marcolino, Erickson R. Nascimento, Richard Jiang

In this paper, we propose a synthetic-aware adverse weather robust algorithm for video stabilization that does not require real data and can be trained only on synthetic data.

Video Stabilization

Text-Driven Video Acceleration: A Weakly-Supervised Reinforcement Learning Method

1 code implementation • 29 Mar 2022 • Washington Ramos, Michel Silva, Edson Araujo, Victor Moura, Keller Oliveira, Leandro Soriano Marcolino, Erickson R. Nascimento

The growth of videos in our digital age and the users' limited time raise the demand for processing untrimmed videos to produce shorter versions conveying the same information.

reinforcement-learning Reinforcement Learning (RL)

Sparse Adversarial Video Attacks with Spatial Transformations

1 code implementation • 10 Nov 2021 • Ronghui Mu, Wenjie Ruan, Leandro Soriano Marcolino, Qiang Ni

In recent years, a significant amount of research efforts concentrated on adversarial attacks on images, while adversarial video attacks have seldom been explored.

Adversarial Attack Bayesian Optimisation +1

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

1 code implementation • CVPR 2020 • Washington Ramos, Michel Silva, Edson Araujo, Leandro Soriano Marcolino, Erickson Nascimento

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.

reinforcement-learning Reinforcement Learning (RL)

Diverse Randomized Agents Vote to Win

no code implementations • NeurIPS 2014 • Albert Jiang, Leandro Soriano Marcolino, Ariel D. Procaccia, Tuomas Sandholm, Nisarg Shah, Milind Tambe

We investigate the power of voting among diverse, randomized software agents.