GUTS: Generalized Uncertainty-Aware Thompson Sampling for Multi-Agent Active Search

no code implementations • 4 Apr 2023 • Nikhil Angad Bakshi, Tejus Gupta, Ramina Ghods, Jeff Schneider

We conduct field tests using our multi-robot system in an unstructured environment with a search area of approximately 75, 000 sq.

Disaster Response Thompson Sampling

SS-MAIL: Self-Supervised Multi-Agent Imitation Learning

no code implementations • 18 Oct 2021 • Akshay Dharmavaram, Tejus Gupta, Jiachen Li, Katia P. Sycara

We show that our method (SS-MAIL) outperforms prior state-of-the-art methods on real-world prediction tasks, as well as on custom-designed synthetic experiments.

Imitation Learning

Predicting Human Strategies in Simulated Search and Rescue Task

no code implementations • 15 Nov 2020 • Vidhi Jain, Rohit Jena, Huao Li, Tejus Gupta, Dana Hughes, Michael Lewis, Katia Sycara

In our efforts to model the rescuer's mind, we begin with a simple simulated search and rescue task in Minecraft with human participants.

f-IRL: Inverse Reinforcement Learning via State Marginal Matching

1 code implementation • 9 Nov 2020 • Tianwei Ni, Harshit Sikchi, YuFei Wang, Tejus Gupta, Lisa Lee, Benjamin Eysenbach

Our method outperforms adversarial imitation learning methods in terms of sample efficiency and the required number of expert trajectories on IRL benchmarks.

Imitation Learning reinforcement-learning +1

A Method for Computing Class-wise Universal Adversarial Perturbations

no code implementations • 1 Dec 2019 • Tejus Gupta, Abhishek Sinha, Nupur Kumari, Mayank Singh, Balaji Krishnamurthy

We present an algorithm for computing class-specific universal adversarial perturbations for deep neural networks.