Shubham Kumar Bharti — accepted AI-conference papers

2024

On the Complexity of Teaching a Family of Linear Behavior Cloning Learners

Shubham Kumar Bharti, Stephen Wright, Adish Singla, Jerry Zhu

NeurIPS 2024poster

We study optimal teaching for a family of Behavior Cloning learners that learn using a linear hypothesis class. In this setup, a knowledgeable teacher can demonstrate a dataset of state and action tuples and is required to teach an optimal policy to an entire family of BC learners using the smallest…

Cited by 0 Source ↗PDF ↗Scholar ↗

2022

Provable Defense against Backdoor Policies in Reinforcement Learning

Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla, Jerry Zhu

NeurIPS 2022accept

We propose a provable defense mechanism against backdoor policies in reinforcement learning under subspace trigger assumption. A backdoor policy is a security threat where an adversary publishes a seemingly well-behaved policy which in fact allows hidden triggers. During deployment, the adversary ca…

Cited by 24 Source ↗PDF ↗code ↗Scholar ↗