Singla, Adish Group A. Singla, Max Planck Institute for Software Systems, Max Planck Society;
NeurIPS-2022-provable-defense-against-backdoor-policies-in-reinforcement-learning-Paper-Conference.pdf (Publisher version), 2MB
Bharti, S., Zhang, X., Singla, A., & Zhu, J. (2022). Provable Defense against Backdoor Policies in Reinforcement Learning. In S. Koyejo, S. Mohamed, A. Agarwal, D. Belgrave, K. Cho, & A. Oh (Eds.), Advances in Neural Information Processing Systems 35 (pp. 14704-14714). Curran Associates, Inc.
