Suda Bharadwaj — accepted AI-conference papers

2021

Decentralized Classification with Assume-Guarantee Planning

Steven Carr, Jesse Quattrociocchi, Suda Bharadwaj, Steven J. Spencer, Anup Parikh, Carol C. Young +3

IROS 2021poster

We study the problem of decentralized classification conducted over a network of mobile sensors. We model the multiagent classification task as a hypothesis testing problem where each sensor has to almost surely find the true hypothesis from a finite set of candidate hypotheses. Each sensor makes no…

Cited by 0 Source ↗Scholar ↗

2021

Temporal-Logic-Based Reward Shaping for Continuing Reinforcement Learning Tasks

Yuqian Jiang, Suda Bharadwaj, Bo Wu, Rishi Shah, Ufuk Topcu, Peter Stone

AAAI 2021technical

In continuing tasks, average-reward reinforcement learning may be a more appropriate problem formulation than the more common discounted reward formulation. As usual, learning an optimal policy in this setting typically requires a large amount of training experiences. Reward shaping is a common appr…

Cited by 64 Source ↗PDF ↗Scholar ↗

2020

Near-Optimal Reactive Synthesis Incorporating Runtime Information

Suda Bharadwaj, Abraham P. Vinod, Rayna Dimitrova, Ufuk Topcu

ICRA 2020poster

We consider the problem of optimal reactive synthesis - compute a strategy that satisfies a mission specification in a dynamic environment, and optimizes a given performance metric. We incorporate task-critical information, that is only available at runtime, into the strategy synthesis in order to i…

Cited by 2 Source ↗Scholar ↗