Publications
Optimally Teaching a Linear Behavior Cloning Agent
Shubham Kumar Bharti, Stephen Wright, Adish Singla, Xiaojin Zhu, Preprint 2023
Provable Defense against Backdoor policies in RL
Shubham Kumar Bharti, Xuezhou Zhang, Adish Singla, Xiaojin Zhu, Neurips 2022
The Game of Hidden Rules: A New Kind of Benchmark Challenge for ML
Eric Pulick, Shubham Kumar Bharti, Yiding Chen, Yonatan Mintz, Paul Kantor, Vicki M. Bier, Preprint 2022
Fair Bandits with Cumulative Parity in Rewards
Shubham Kumar Bharti, Kangwook Lee, Xiaojin Zhu, Preprint 2021
The Sample Complexity of Teaching-by-Reinforcement on Q-Learning
Xuezhou Zhang, Shubham Kumar Bharti, Yuzhe Ma, Adish Singla and Xiaojin Zhu, AAAI 2021
Multitask Neural Networks meets Multitask Gaussian Processes
Karthikeyan K, Shubham Kumar Bharti, Piyush Rai, Arxiv 2019
