Add publication: Reinforcement Learning...

content/publication/reinforcement-learning-for-falsification-of-dynamic-driving-scenarios-2026.md

@@ -0,0 +1,25 @@
++++
+title = "Reinforcement Learning for Falsification of Dynamic Driving Scenarios"
+publication = "Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems"
+journal = "Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems"
+year = "2026"
+date = "2026-05-25"
+abstract = "Falsification has been widely used to find failure cases for cyber-physical systems (CPS). In the domain of autonomous driving, falsification has recently been applied to find adversarial driving maneuvers which cause other vehicles to crash. In this work, we propose a reinforcement learning (RL)-based falsification framework that can discover complex adversarial maneuvers in diverse driving scenarios. Finally, we compare our approach to existing falsification methods, both in terms of their efficiency at finding counter-examples as well as the diversity and quality of their counter-examples. Our results suggest that RL-based falsification can be an effective tool for testing and validating autonomous vehicle systems."
+url_dataset = ""
+url_pdf = "https://dl.acm.org/doi/epdf/10.65109/PFBJ1092"
+url_project = ""
+url_slides = ""
+url_video = ""
+[[authors]]
+  name = "Chang, Oliver"
+  is_member = true
+[[authors]]
+  name = "Vargas, Kay"
+  is_member = false
+[[authors]]
+  name = "Gilpin, Leilani H"
+  is_member = true
+[[authors]]
+  name = "Fremont, Daniel J"
+  is_member = false
++++

publications.bib

@@ -293,3 +293,14 @@ @article{la2025guaranteed
   url_pdf  = {https://arxiv.org/pdf/2511.20934},
   abstract = {While neurons are the basic units of deep neural networks, it is still unclear what they learn and if their knowledge is aligned with that of humans. Compositional explanations aim to answer this question by describing the spatial alignment between neuron activations and concepts through logical rules. These logical descriptions are typically computed via a search over all possible concept combinations. Since computing the spatial alignment over the entire state space is computationally infeasible, the literature commonly adopts beam search to restrict the space. However, beam search cannot provide any theoretical guarantees of optimality, and it remains unclear how close current explanations are to the true optimum. In this theoretical paper, we address this gap by introducing the first framework for computing guaranteed optimal compositional explanations. Specifically, we propose: (i) a decomposition that identifies the factors influencing the spatial alignment, (ii) a heuristic to estimate the alignment at any stage of the search, and (iii) the first algorithm that can compute optimal compositional explanations within a feasible time. Using this framework, we analyze the differences between optimal and non-optimal explanations in the most popular settings for compositional explanations, the computer vision domain and Convolutional Neural Networks. In these settings, we demonstrate that 10-40 percent of explanations obtained with beam search are suboptimal when overlapping concepts are involved. Finally, we evaluate a beam-search variant guided by our proposed decomposition and heuristic, showing that it matches or improves runtime over prior methods while offering greater flexibility in hyperparameters and computational resources.},
 }
+
+@inproceedings{chang2026reinforcement,
+  title = {Reinforcement Learning for Falsification of Dynamic Driving Scenarios},
+  author = {Chang, Oliver and Vargas, Kay and Gilpin, Leilani H and Fremont, Daniel J},
+  booktitle = {Proceedings of the 25th International Conference on Autonomous Agents and Multiagent Systems},
+  pages = {3636-3638},
+  date = {2026-05-25},
+ organization = {International Foundation for Autonomous Agents and Multiagent Systems},
+url_pdf = {https://dl.acm.org/doi/epdf/10.65109/PFBJ1092},
+  abstract  = {Falsification has been widely used to find failure cases for cyber-physical systems (CPS). In the domain of autonomous driving, falsification has recently been applied to find adversarial driving maneuvers which cause other vehicles to crash. In this work, we propose a reinforcement learning (RL)-based falsification framework that can discover complex adversarial maneuvers in diverse driving scenarios. Finally, we compare our approach to existing falsification methods, both in terms of their efficiency at finding counter-examples as well as the diversity and quality of their counter-examples. Our results suggest that RL-based falsification can be an effective tool for testing and validating autonomous vehicle systems.},
+}