no code implementations • 7 Oct 2022 • Andrew Silva, Pradyumna Tambwekar, Matthew Gombolay
Federated learning is a training paradigm that learns from multiple distributed users without aggregating data on a centralized server.
no code implementations • 21 Jun 2022 • Esmaeil Seraj, Andrew Silva, Matthew Gombolay
Our approach enables UAVs to infer the latent fire propagation dynamics for time-extended coordination in safety-critical conditions.
no code implementations • 18 Feb 2022 • Andrew Silva, Katherine Metcalf, Nicholas Apostoloff, Barry-John Theobald
Federated learning enables the deployment of machine learning to problems for which centralized data collection is impractical.
1 code implementation • 4 Feb 2022 • Rohan Paleja, Yaru Niu, Andrew Silva, Chace Ritchie, Sugju Choi, Matthew Gombolay
While the performance of these approaches warrants real-world adoption, these policies lack interpretability, limiting deployability in the safety-critical and legally-regulated domain of autonomous driving (AD).
no code implementations • NAACL 2021 • Andrew Silva, Pradyumna Tambwekar, Matthew Gombolay
The ease of access to pre-trained transformers has enabled developers to leverage large-scale language models to build exciting applications for their users.
no code implementations • 12 Feb 2021 • Andrew Silva, Barry-John Theobald, Nicholas Apostoloff
Automatic speech recognition (ASR) is widely used in consumer electronics.
Automatic Speech Recognition Automatic Speech Recognition (ASR) +1
1 code implementation • 18 Jan 2021 • Pradyumna Tambwekar, Andrew Silva, Nakul Gopalan, Matthew Gombolay
Human-AI policy specification is a novel procedure we define in which humans can collaboratively warm-start a robot's reinforcement learning policy.
1 code implementation • 3 Dec 2020 • Andrew Silva, Rohit Chopra, Matthew Gombolay
As machine learning is increasingly deployed in the real world, it is paramount that we develop the tools necessary to analyze the decision-making of the models we train and deploy to end-users.
1 code implementation • NeurIPS 2020 • Rohan Paleja, Andrew Silva, Letian Chen, Matthew Gombolay
Resource scheduling and coordination is an NP-hard optimization requiring an efficient allocation of agents to a set of tasks with upper- and lower bound temporal and resource constraints.
2 code implementations • 22 Mar 2019 • Andrew Silva, Taylor Killian, Ivan Dario Jimenez Rodriguez, Sung-Hyun Son, Matthew Gombolay
Decision trees are ubiquitous in machine learning for their ease of use and interpretability.
1 code implementation • 16 Mar 2019 • Esmaeil Seraj, Andrew Silva, Matthew Gombolay
Wildfires are destructive and inflict massive, irreversible harm to victims' lives and natural resources.
1 code implementation • 15 Feb 2019 • Andrew Silva, Matthew Gombolay
Deep reinforcement learning has been successful in a variety of tasks, such as game playing and robotic manipulation.
no code implementations • 2 Jan 2019 • Meera Hahn, Andrew Silva, James M. Rehg
We describe a novel cross-modal embedding space for actions, named Action2Vec, which combines linguistic cues from class labels with spatio-temporal features derived from video clips.