Alert button
Picture for Ufuk Topcu

Ufuk Topcu

Alert button

Task-aware Distributed Source Coding under Dynamic Bandwidth

May 24, 2023
Po-han Li, Sravan Kumar Ankireddy, Ruihan Zhao, Hossein Nourkhiz Mahjoub, Ehsan Moradi-Pari, Ufuk Topcu, Sandeep Chinchali, Hyeji Kim

Figure 1 for Task-aware Distributed Source Coding under Dynamic Bandwidth
Figure 2 for Task-aware Distributed Source Coding under Dynamic Bandwidth
Figure 3 for Task-aware Distributed Source Coding under Dynamic Bandwidth
Figure 4 for Task-aware Distributed Source Coding under Dynamic Bandwidth
Viaarxiv icon

Efficient Sensitivity Analysis for Parametric Robust Markov Chains

May 01, 2023
Thom Badings, Sebastian Junges, Ahmadreza Marandi, Ufuk Topcu, Nils Jansen

Figure 1 for Efficient Sensitivity Analysis for Parametric Robust Markov Chains
Figure 2 for Efficient Sensitivity Analysis for Parametric Robust Markov Chains
Figure 3 for Efficient Sensitivity Analysis for Parametric Robust Markov Chains
Figure 4 for Efficient Sensitivity Analysis for Parametric Robust Markov Chains
Viaarxiv icon

Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning

Mar 31, 2023
Shenghui Chen, Yue Yu, David Fridovich-Keil, Ufuk Topcu

Figure 1 for Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning
Figure 2 for Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning
Figure 3 for Soft-Bellman Equilibrium in Affine Markov Games: Forward Solutions and Inverse Learning
Viaarxiv icon

On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples

Mar 07, 2023
Mustafa O. Karabag, Ufuk Topcu

Figure 1 for On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples
Figure 2 for On the Sample Complexity of Vanilla Model-Based Offline Reinforcement Learning with Dependent Samples
Viaarxiv icon

Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations

Feb 28, 2023
Ruihan Zhao, Ufuk Topcu, Sandeep Chinchali, Mariano Phielipp

Figure 1 for Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Figure 2 for Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Figure 3 for Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Figure 4 for Learning Sparse Control Tasks from Pixels by Latent Nearest-Neighbor-Guided Explorations
Viaarxiv icon

Differential Privacy in Cooperative Multiagent Planning

Jan 20, 2023
Bo Chen, Calvin Hawkins, Mustafa O. Karabag, Cyrus Neary, Matthew Hale, Ufuk Topcu

Figure 1 for Differential Privacy in Cooperative Multiagent Planning
Figure 2 for Differential Privacy in Cooperative Multiagent Planning
Figure 3 for Differential Privacy in Cooperative Multiagent Planning
Figure 4 for Differential Privacy in Cooperative Multiagent Planning
Viaarxiv icon

Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control

Jan 09, 2023
Adam J. Thorpe, Cyrus Neary, Franck Djeumou, Meeko M. K. Oishi, Ufuk Topcu

Figure 1 for Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control
Figure 2 for Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control
Figure 3 for Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control
Figure 4 for Physics-Informed Kernel Embeddings: Integrating Prior System Knowledge with Data-Driven Control
Viaarxiv icon

Task-Guided IRL in POMDPs that Scales

Dec 30, 2022
Franck Djeumou, Christian Ellis, Murat Cubuktepe, Craig Lennon, Ufuk Topcu

Figure 1 for Task-Guided IRL in POMDPs that Scales
Figure 2 for Task-Guided IRL in POMDPs that Scales
Figure 3 for Task-Guided IRL in POMDPs that Scales
Figure 4 for Task-Guided IRL in POMDPs that Scales
Viaarxiv icon

Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models

Dec 04, 2022
Yunhao Yang, Jean-Raphaël Gaglione, Ufuk Topcu

Figure 1 for Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models
Figure 2 for Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models
Figure 3 for Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models
Figure 4 for Learning Automata-Based Task Knowledge Representation from Large-Scale Generative Language Models
Viaarxiv icon

Learning Temporal Logic Properties: an Overview of Two Recent Methods

Dec 02, 2022
Jean-Raphaël Gaglione, Rajarshi Roy, Nasim Baharisangari, Daniel Neider, Zhe Xu, Ufuk Topcu

Figure 1 for Learning Temporal Logic Properties: an Overview of Two Recent Methods
Figure 2 for Learning Temporal Logic Properties: an Overview of Two Recent Methods
Figure 3 for Learning Temporal Logic Properties: an Overview of Two Recent Methods
Viaarxiv icon