Completed Projects

Content Filters

Results

Adversarial Attacks Against Deep Reinforcement Learning Policies for Strategy Games

Agnostic Reinforcement Learning

Automatic Curriculum Generation and Emergent Complexity via Inter-agent Competition

Autonomous Skill Discovery Through Self-Supervised Exploration

Barcode Image Denoise - RL Approach

Better Visual Representations through Language Supervision

Combining Causal Reasoning and Information Theory to Empower Humans through Human-Agent Collaboration

Differentiable Optimization for Game Theoretic Formulations

Disentangling Input Signals for Robust Computer Vision

Distributed Probabilistic Inference on Ray

Echo State Transformers

Efficient Object Detection with Super High-Resolution Image

Enabling Broader Learning Through Simplified and Personalized Summaries

Generalization Bounds for Interpolating Deep Neural Networks

Generalizing Neural Radiance Fields

Graph Data Augmentation for Computer Systems

Knowledge Transferable Bayesian Optimization

Learning Non-Intuitive Physics in Children and Adults

Learning Robust Robot Policies to Manipulate and Fill Deformable Bags

Long-Horizon Decision-Making with Energy-Based Models

LP-based Algorithms for Reinforcement Learning

Mitigating Emergent Biases in Online Learning

Multi-task Learning with Safe and Differentiable Policies

Neural Program Synthesis from Diverse and Distant Context

On Theoretical Foundations for Transfer Learning

Semantic Depth Extraction for Indoor Scenes

Smart Practice: Learning to Practice Skills from Demonstrations

Towards Trustworthy Reinforcement Learning

Unsupervised Learning of Visual Context from Instance Segmentation

Visual Locomotion: Synergistic Approach via Perception and Proprioception