Subramanian Ramamoorthy

Latest

• Composing Diverse Policies for Temporally Extended Tasks
• Learning robotic ultrasound scanning using probabilistic temporal ranking
• Disentangled Relational Representations for Explaining and Learning from Demonstration
• Using Causal Analysis to Learn Specifications from Task Demonstrations
• DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL
• Learning from demonstration of trajectory preferences through causal modeling and inference