TY - INPR A1 - Rößle, Dominik A1 - Xie, Xujun A1 - Mohan, Adithya A1 - Thirugnana Sambandham, Venkatesh A1 - Cremers, Daniel A1 - Schön, Torsten T1 - DrivIng: A Large-Scale Multimodal Driving Dataset with Full Digital Twin Integration UR - https://doi.org/10.48550/arXiv.2601.15260 Y1 - 2026 UR - https://doi.org/10.48550/arXiv.2601.15260 PB - arXiv CY - Ithaca ER - TY - JOUR A1 - Mohan, Adithya A1 - Schön, Torsten T1 - Toward Robust Agents: A Survey of Adversarial Attacks and Defenses in Deep Reinforcement Learning JF - IEEE Access N2 - Deep Reinforcement Learning (DRL) has demonstrated remarkable success in autonomous decision-making across diverse domains, including robotics, autonomous driving, and game playing. However, recent studies have uncovered a critical vulnerability: DRL agents are highly susceptible to adversarial attacks that can significantly degrade their performance or lead to catastrophic failure. These attacks exploit different components of the learning pipeline observations, actions, rewards, and policies exposing new challenges unique to DRL compared to supervised learning. This survey provides a comprehensive examination of adversarial threats and corresponding defense mechanisms within the DRL paradigm. This also aims to serve as a foundational reference for researchers and practitioners seeking to understand and mitigate adversarial vulnerabilities in DRL. UR - https://doi.org/10.1109/ACCESS.2026.3657855 Y1 - 2026 UR - https://doi.org/10.1109/ACCESS.2026.3657855 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-66232 SN - 2169-3536 VL - 14 SP - 14481 EP - 14497 PB - IEEE CY - New York ER - TY - INPR A1 - Chandra Sekaran, Karthikeyan A1 - Geisler, Markus A1 - Rößle, Dominik A1 - Mohan, Adithya A1 - Cremers, Daniel A1 - Utschick, Wolfgang A1 - Botsch, Michael A1 - Huber, Werner A1 - Schön, Torsten T1 - UrbanIng-V2X: A Large-Scale Multi-Vehicle, Multi-Infrastructure Dataset Across Multiple Intersections for Cooperative Perception UR - https://doi.org/10.48550/arXiv.2510.23478 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2510.23478 PB - arXiv CY - Ithaca ER - TY - INPR A1 - Mohan, Adithya A1 - Rößle, Dominik A1 - Cremers, Daniel A1 - Schön, Torsten T1 - Advancing Robustness in Deep Reinforcement Learning with an Ensemble Defense Approach UR - https://doi.org/10.48550/arXiv.2507.17070 Y1 - 2025 UR - https://doi.org/10.48550/arXiv.2507.17070 PB - arXiv CY - Ithaca ER - TY - CHAP A1 - Karpenahalli Ramakrishna, Chidvilas A1 - Mohan, Adithya A1 - Zeinaly, Zahra A1 - Belzner, Lenz ED - Rocha, Ana Paula ED - Steels, Luc ED - van den Herik, Jaap T1 - The Evolution of Criticality in Deep Reinforcement Learning T2 - Proceedings of the 17th International Conference on Agents and Artificial Intelligence (ICAART 2025) - Volume 3 N2 - In Reinforcement Learning (RL), certain states demand special attention due to their significant influence on outcomes; these are identified as critical states. The concept of criticality is essential for the development of effective and robust policies and to improve overall trust in RL agents in real-world applications like autonomous driving. The current paper takes a deep dive into criticality and studies the evolution of criticality throughout training. The experiments are conducted on a new, simple yet intuitive continuous cliff maze environment and the Highway-env autonomous driving environment. Here, a novel finding is reported that criticality is not only learnt by the agent but can also be unlearned. We hypothesize that diversity in experiences is necessary for effective criticality quantification which is majorly driven by the chosen exploration strategy. This close relationship between exploration and criticality is studied utilizing two different strategies namely the ex ponential ε-decay and the adaptive ε-decay. The study supports the idea that effective exploration plays a crucial role in accurately identifying and understanding critical states. UR - https://doi.org/10.5220/0013114200003890 Y1 - 2025 UR - https://doi.org/10.5220/0013114200003890 UR - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:bvb:573-57992 SN - 978-989-758-737-5 SP - 217 EP - 224 PB - SciTePress CY - Setúbal ER -