Subramanian Ramamoorthy

Latest

• Learning from Demonstration with Weakly Supervised Disentanglement
• Composing Diverse Policies for Temporally Extended Tasks
• Disentangled Relational Representations for Explaining and Learning from Demonstration
• Hybrid system identification using switching density networks
• Using Causal Analysis to Learn Specifications from Task Demonstrations
• DynoPlan: Combining Motion Planning and Deep Neural Network based Controllers for Safe HRL
• Interpretable Latent Spaces for Learning from Demonstration
• Grounding Symbols in Multi-Modal Instructions