Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Ufuk Topcu

Self-Supervised Online Reward Shaping in Sparse-Reward Environments


Mar 08, 2021
Farzan Memarian, Wonjoon Goo, Rudolf Lioutikov, Ufuk Topcu, Scott Niekum


  Access Paper or Ask Questions

Function Approximation via Sparse Random Features


Mar 04, 2021
Abolfazl Hashemi, Hayden Schaeffer, Robert Shi, Ufuk Topcu, Giang Tran, Rachel Ward


  Access Paper or Ask Questions

A 3D Printing Hexacopter: Design and Demonstration


Mar 02, 2021
Alexander Nettekoven, Ufuk Topcu


  Access Paper or Ask Questions

Physical-Layer Security via Distributed Beamforming in the Presence of Adversaries with Unknown Locations


Feb 28, 2021
Yagiz Savas, Abolfazl Hashemi, Abraham P. Vinod, Brian M. Sadler, Ufuk Topcu

* 5 pages, 3 figures 

  Access Paper or Ask Questions

Privacy-Preserving Teacher-Student Deep Reinforcement Learning


Feb 18, 2021
Parham Gohari, Bo Chen, Bo Wu, Matthew Hale, Ufuk Topcu

* Under double-blind review 

  Access Paper or Ask Questions

Safe Multi-Agent Reinforcement Learning via Shielding


Feb 02, 2021
Ingy Elsayed-Aly, Suda Bharadwaj, Christopher Amato, Rüdiger Ehlers, Ufuk Topcu, Lu Feng

* 8 pages, 11 figures and 2 tables, to be published in AAMAS 2021 

  Access Paper or Ask Questions

Multiple Plans are Better than One: Diverse Stochastic Planning


Dec 31, 2020
Mahsa Ghasemi, Evan Scope Crafts, Bo Zhao, Ufuk Topcu

* Mahsa Ghasemi and Evan Scope Crafts have contributed equally to the manuscript 

  Access Paper or Ask Questions

Towards online monitoring and data-driven control: a study of segmentation algorithms for infrared images of the powder bed


Nov 18, 2020
Alexander Nettekoven, Scott Fish, Joseph Beaman, Ufuk Topcu


  Access Paper or Ask Questions

Assured Autonomy: Path Toward Living With Autonomous Systems We Can Trust


Oct 27, 2020
Ufuk Topcu, Nadya Bliss, Nancy Cooke, Missy Cummings, Ashley Llorens, Howard Shrobe, Lenore Zuck

* A Computing Community Consortium (CCC) workshop report, 28 pages 

  Access Paper or Ask Questions

Minimum-Violation Planning for Autonomous Systems: Theoretical and Practical Considerations


Sep 24, 2020
Tichakorn Wongpiromsarn, Konstantin Slutsky, Emilio Frazzoli, Ufuk Topcu


  Access Paper or Ask Questions

Robust Finite-State Controllers for Uncertain POMDPs


Sep 24, 2020
Murat Cubuktepe, Nils Jansen, Sebastian Junges, Ahmadreza Marandi, Marnix Suilen, Ufuk Topcu


  Access Paper or Ask Questions

BP-RRT: Barrier Pair Synthesis for Temporal Logic Motion Planning


Sep 05, 2020
Binghan He, Jaemin Lee, Ufuk Topcu, Luis Sentis

* 6 pages, 5 figures. Accepted for publication in IEEE Conference on Decision and Control (CDC) copyright 2020 IEEE 

  Access Paper or Ask Questions

Near-Optimal Reactive Synthesis Incorporating Runtime Information


Jul 31, 2020
Suda Bharadwaj, Abraham P. Vinod, Rayna Dimitrova, Ufuk Topcu

* Presented at ICRA2020 

  Access Paper or Ask Questions

Reward Machines for Cooperative Multi-Agent Reinforcement Learning


Jul 03, 2020
Cyrus Neary, Zhe Xu, Bo Wu, Ufuk Topcu


  Access Paper or Ask Questions

Temporal-Logic-Based Reward Shaping for Continuing Learning Tasks


Jul 03, 2020
Yuqian Jiang, Sudarshanan Bharadwaj, Bo Wu, Rishi Shah, Ufuk Topcu, Peter Stone


  Access Paper or Ask Questions

Active Finite Reward Automaton Inference and Reinforcement Learning Using Queries and Counterexamples


Jun 28, 2020
Zhe Xu, Bo Wu, Daniel Neider, Ufuk Topcu


  Access Paper or Ask Questions

Scalable Synthesis of Minimum-Information Linear-Gaussian Control by Distributed Optimization


Apr 11, 2020
Murat Cubuktepe, Takashi Tanaka, Ufuk Topcu

* Submitted to 2020 CDC 

  Access Paper or Ask Questions

Verifiable RNN-Based Policies for POMDPs Under Temporal Logic Constraints


Feb 13, 2020
Steven Carr, Nils Jansen, Ufuk Topcu

* 8 pages, 5 figures, 1 table 

  Access Paper or Ask Questions

Adaptive Teaching of Temporal Logic Formulas to Learners with Preferences


Jan 27, 2020
Zhe Xu, Yuxin Chen, Ufuk Topcu

* 25 pages 

  Access Paper or Ask Questions

Active Task-Inference-Guided Deep Inverse Reinforcement Learning


Jan 24, 2020
Farzan Memarian, Zhe Xu, Bo Wu, Min Wen, Ufuk Topcu


  Access Paper or Ask Questions

Learning and Planning for Time-Varying MDPs Using Maximum Likelihood Estimation


Nov 29, 2019
Melkior Ornik, Ufuk Topcu


  Access Paper or Ask Questions

Strategy Synthesis for Surveillance-Evasion Games with Learning-Enabled Visibility Optimization


Nov 18, 2019
Suda Bharadwaj, Louis Ly, Bo Wu, Richard Tsai, Ufuk Topcu


  Access Paper or Ask Questions

Decentralized Runtime Synthesis of Shields for Multi-Agent Systems


Oct 23, 2019
Dhananjay Raju, Suda Bharadwaj, Ufuk Topcu


  Access Paper or Ask Questions

Online Active Perception for Partially Observable Markov Decision Processes with Limited Budget


Oct 04, 2019
Mahsa Ghasemi, Ufuk Topcu

* Accepted for publication in Conference on Decision and Control (CDC) Proceedings, 2019 

  Access Paper or Ask Questions

Differentially Private Controller Synthesis With Metric Temporal Logic Specifications


Sep 29, 2019
Zhe Xu, Kasra Yazdani, Matthew T. Hale, Ufuk Topcu


  Access Paper or Ask Questions

Identifying Low-Dimensional Structures in Markov Chains: A Nonnegative Matrix Factorization Approach


Sep 27, 2019
Mahsa Ghasemi, Abolfazl Hashemi, Haris Vikalo, Ufuk Topcu


  Access Paper or Ask Questions

Controller Synthesis for Multi-Agent Systems With Intermittent Communication: A Metric Temporal Logic Approach


Sep 22, 2019
Zhe Xu, Federico M. Zegers, Bo Wu, Warren Dixon, Ufuk Topcu


  Access Paper or Ask Questions

Joint Inference of Reward Machines and Policies for Reinforcement Learning


Sep 12, 2019
Zhe Xu, Ivan Gavran, Yousef Ahmad, Rupak Majumdar, Daniel Neider, Ufuk Topcu, Bo Wu


  Access Paper or Ask Questions

Transfer of Temporal Logic Formulas in Reinforcement Learning


Sep 10, 2019
Zhe Xu, Ufuk Topcu

* IJCAI'19 

  Access Paper or Ask Questions