A5038595846- Formal Methods in Verification
- Advanced Authentication Protocols Security
- Software Reliability and Analysis Research
- Vehicular Ad Hoc Networks (VANETs)
- Wireless Body Area Networks
- Adversarial Robustness in Machine Learning
- Smart Grid Security and Resilience
- Reinforcement Learning in Robotics
- Safety Systems Engineering in Autonomy
- Software Testing and Debugging Techniques
University of Virginia
2020-2024
Multi-agent reinforcement learning (MARL) has been increasingly used in a wide range of safety-critical applications, which require guaranteed safety (e.g., no unsafe states are ever visited) during the process.Unfortunately, current MARL methods do not have guarantees. Therefore, we present two shielding approaches for safe MARL. In centralized shielding, synthesize single shield to monitor all agents' joint actions and correct any action if necessary. factored multiple shields based on...
Probabilistic model checking can provide formal guarantees on the behavior of stochastic models relating to a wide range quantitative properties, such as runtime, energy consumption or cost. But decision making is typically with respect expected value these quantities, which mask important aspects full probability distribution possibility high-risk, low-probability events multimodalities. We propose distributional extension probabilistic checking, applicable discrete-time Markov chains...