4 papers
Steerable Pluralistic Policy Alignment from Anonymized Crowd Feedback
Akansha Kalra, Ellen R. Novoseller, Vernon J. Lawhern +1
Pluralistic alignment requires AI systems to learn from diverse populations whose preferences may reflect heterogeneous or even conflicting objectives, and to personalize their beh…
Dataset Poisoning Attacks on Behavioral Cloning Policies
Akansha Kalra, Soumil Datta, Ethan Gilmore +3
Behavior Cloning (BC) is a popular framework for training sequential decision policies from expert demonstrations via supervised learning. As these policies are increasingly being…
How Vulnerable Is My Learned Policy? Universal Adversarial Perturbation Attacks On Modern Behavior Cloning Policies
Akansha Kalra, Basavasagar Patil, Guanhong Tao +1
Imitation learning, also known as learning from demonstrations, is a popular approach to train AI models; however, the vulnerability of these models to adversarial attacks remains…
Can Differentiable Decision Trees Enable Interpretable Reward Learning from Human Feedback?
Akansha Kalra, Daniel S. Brown
Reinforcement Learning from Human Feedback (RLHF) has emerged as a popular paradigm for capturing human intent to alleviate the challenges of hand-crafting the reward values. Despi…