5 papers
Constrained Reinforcement Learning Under Model Mismatch
Zhongchang Sun, Sihong He, Fei Miao +1
Existing studies on constrained reinforcement learning (RL) may obtain a well-performing policy in the training environment. However, when deployed in a real environment, it may ea…
Robust Multi-Agent Reinforcement Learning with State Uncertainty
Sihong He, Songyang Han, Sanbao Su +3
In real-world multi-agent reinforcement learning (MARL) applications, agents may not have perfect state information (e.g., due to inaccurate measurement or malicious attacks), whic…
Surrogate Lagrangian Relaxation: A Path To Retrain-free Deep Neural Network Pruning
Shanglin Zhou, Mikhail A. Bragin, Lynn Pepin +3
Network pruning is a widely used technique to reduce computation cost and model size for deep neural networks. However, the typical three-stage pipeline significantly increases the…
Privacy-preserving and Uncertainty-aware Federated Trajectory Prediction for Connected Autonomous Vehicles
Muzi Peng, Jiangwei Wang, Dongjin Song +2
Deep learning is the method of choice for trajectory prediction for autonomous vehicles. Unfortunately, its data-hungry nature implicitly requires the availability of sufficiently…
Shared Information-Based Safe And Efficient Behavior Planning For Connected Autonomous Vehicles
Songyang Han, Shanglin Zhou, Lynn Pepin +3
The recent advancements in wireless technology enable connected autonomous vehicles (CAVs) to gather data via vehicle-to-vehicle (V2V) communication, such as processed LIDAR and ca…