6 papers
NeSy-CSA: A Neuro-Symbolic Framework for Open-Ended Critical Scenario Attribution
Qitong Chu, Xunjie He, Chen Deng +2
Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems. Reasoning about such criti…
Intelligent Resilience Testing for Decision-Making Agents with Dual-Mode Surrogate Adaptation
Jingxuan Yang, Weichao Xu, Yuchen Shi +3
Testing and evaluating decision-making agents remains challenging due to unknown system architectures, limited access to internal states, and the vastness of high-dimensional scena…
Fault-Tolerant MARL for CAVs under Observation Perturbations for Highway On-Ramp Merging
Yuchen Shi, Huaxin Pei, Yi Zhang +1
Multi-Agent Reinforcement Learning (MARL) holds significant promise for enabling cooperative driving among Connected and Automated Vehicles (CAVs). However, its practical applicati…
DiCriTest: Testing Scenario Generation for Decision-Making Agents Considering Diversity and Criticality
Qitong Chu, Yufeng Yue, Danya Yao +1
The growing deployment of decision-making agents in dynamic environments increases the demand for safety verification. While critical testing scenario generation has emerged as an…
Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach
Weichao Xu, Huaxin Pei, Jingxuan Yang +3
Recent advances in decision-making policies have led to significant progress in fields such as autonomous driving and robotics. However, testing these policies remains crucial with…
Towards Fault Tolerance in Multi-Agent Reinforcement Learning
Yuchen Shi, Huaxin Pei, Liang Feng +2
Agent faults pose a significant threat to the performance of multi-agent reinforcement learning (MARL) algorithms, introducing two key challenges. First, agents often struggle to e…