142 citations · 712 across the 76 of their papers we have counts for
6 papers · 1 filter
Generating Out-Of-Distribution Scenarios Using Language Models
Erfan Aasi, Phat Nguyen, Shiva Sreeram +3
The deployment of autonomous vehicles controlled by machine learning techniques requires extensive testing in diverse real-world environments, robust handling of edge cases and out…
DecTrain: Deciding When to Train a Monocular Depth DNN Online
Zih-Sing Fu, Soumya Sudhakar, Sertac Karaman +1
Deep neural networks (DNNs) can deteriorate in accuracy when deployment data differs from training data. While performing online training at all timesteps can improve accuracy, it…
Neighborhood Mixup Experience Replay: Local Convex Interpolation for Improved Sample Efficiency in Continuous Control Tasks
Ryan Sander, Wilko Schwarting, Tim Seyde +3
Experience replay plays a crucial role in improving the sample efficiency of deep reinforcement learning agents. Recent advances in experience replay propose using Mixup (Zhang et…
Deep Latent Competition: Learning to Race Using Visual Control Policies in Latent Space
Wilko Schwarting, Tim Seyde, Igor Gilitschenski +4
Learning competitive behaviors in multi-agent settings such as racing requires long-term reasoning about potential adversarial interactions. This paper presents Deep Latent Competi…
Learning to Plan Optimistically: Uncertainty-Guided Deep Exploration via Latent Model Ensembles
Tim Seyde, Wilko Schwarting, Sertac Karaman +1
Learning complex robot behaviors through interaction requires structured exploration. Planning should target interactions with the potential to optimize long-term performance, whil…
Variational End-to-End Navigation and Localization
Alexander Amini, Guy Rosman, Sertac Karaman +1
Deep learning has revolutionized the ability to learn "end-to-end" autonomous vehicle control directly from raw sensory data. While there have been recent extensions to handle form…