
-
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos
We present an approach for physical imitation from human videos for robo...
read it
-
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Evolution in nature illustrates that the creatures' biological structure...
read it
-
Skill Transfer via Partially Amortized Hierarchical Planning
To quickly solve new tasks in complex environments, intelligent agents n...
read it
-
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
Multi-goal reaching is an important problem in reinforcement learning ne...
read it
-
Action Concept Grounding Network for Semantically-Consistent Video Generation
Recent works in self-supervised video prediction have mainly focused on ...
read it
-
Solving Physics Puzzles by Reasoning about Paths
We propose a new deep learning model for goal-driven tasks that require ...
read it
-
Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion
Understanding the gap between simulation andreality is critical for rein...
read it
-
Conservative Safety Critics for Exploration
Safe exploration presents a major challenge in reinforcement learning (R...
read it
-
D2RL: Deep Dense Architectures in Reinforcement Learning
While improvements in deep learning architectures have played a crucial ...
read it
-
Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
We present a hierarchical framework that combines model-based control an...
read it
-
OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Real-world tasks often exhibit a compositional structure that contains a...
read it
-
Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter
When searching for objects in cluttered environments, it is often necess...
read it
-
Counterfactual Data Augmentation using Locally Factored Dynamics
Many dynamic processes, including common scenarios in robotic control an...
read it
-
Causal Discovery in Physical Systems from Videos
Causal discovery is at the core of human cognition. It enables us to rea...
read it
-
De-anonymization of authors through arXiv submissions during double-blind review
In this paper, we investigate the effects of releasing arXiv preprints o...
read it
-
Maximum Entropy Models for Fast Adaptation
Deep Neural Networks have shown great promise on a variety of downstream...
read it
-
Experience Replay with Likelihood-free Importance Weights
The use of past experiences to accelerate temporal difference (TD) learn...
read it
-
LEAF: Latent Exploration Along the Frontier
Self-supervised goal proposal and reaching is a key component for explor...
read it
-
Dynamics-Aware Latent Space Reachability for Exploration in Temporally-Extended Tasks
Self-supervised goal proposal and reaching is a key component of efficie...
read it
-
Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning
Traditional robotic approaches rely on an accurate model of the environm...
read it
-
DIBS: Diversity inducing Information Bottleneck in Model Ensembles
Although deep learning models have achieved state-of-the-art performance...
read it
-
Semi-Supervised StyleGAN for Disentanglement Learning
Disentanglement learning is crucial for obtaining disentangled represent...
read it
-
Curriculum By Texture
Convolutional Neural Networks (CNNs) have shown impressive performance i...
read it
-
Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos
Unsupervised landmark learning is the task of learning semantic keypoint...
read it
-
InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers
Continuous Normalizing Flows (CNFs) have emerged as promising deep gener...
read it
-
Motion Reasoning for Goal-Based Imitation Learning
We address goal-based imitation learning, where the aim is to output the...
read it
-
IRIS: Implicit Reinforcement without Interaction at Scale for Learning Control from Offline Robot Manipulation Data
Learning from offline task demonstrations is a problem of great interest...
read it
-
Scaling Robot Supervision to Hundreds of Hours with RoboTurk: Robotic Manipulation Dataset through Human Reasoning and Dexterity
Large, richly annotated datasets have accelerated progress in fields suc...
read it
-
A Programmable Approach to Model Compression
Deep neural networks frequently contain far more weights, represented at...
read it
-
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation
The fundamental challenge of planning for multi-step manipulation is to ...
read it
-
Controlling Assistive Robots with Learned Latent Actions
Assistive robots enable users with disabilities to perform everyday task...
read it
-
AC-Teach: A Bayesian Actor-Critic Method for Policy Learning with an Ensemble of Suboptimal Teachers
The exploration mechanism used by a Deep Reinforcement Learning (RL) age...
read it
-
Video Interpolation and Prediction with Unsupervised Landmarks
Prediction and interpolation for long-range video data involves the comp...
read it
-
Continuous Relaxation of Symbolic Planner for One-Shot Imitation Learning
We address one-shot imitation learning, where the goal is to execute a p...
read it
-
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks
Contact-rich manipulation tasks in unstructured environments often requi...
read it
-
Variable Impedance Control in End-Effector Space: An Action Space for Reinforcement Learning in Contact-Rich Tasks
Reinforcement Learning (RL) of contact-rich manipulation tasks has yield...
read it
-
Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
When operating in unstructured environments such as warehouses, homes, a...
read it
-
RoboTurk: A Crowdsourcing Platform for Robotic Skill Learning through Imitation
Imitation Learning has empowered recent advances in learning robotic man...
read it
-
Making Sense of Vision and Touch: Self-Supervised Learning of Multimodal Representations for Contact-Rich Tasks
Contact-rich manipulation tasks in unstructured environments often requi...
read it
-
Neural Task Graphs: Generalizing to Unseen Tasks from a Single Video Demonstration
Our goal is for a robot to execute a previously unseen task based on a s...
read it
-
Learning Task-Oriented Grasping for Tool Manipulation from Simulated Self-Supervision
Tool manipulation is vital for facilitating robots to complete challengi...
read it
-
Composing Meta-Policies for Autonomous Driving Using Hierarchical Deep Reinforcement Learning
Rather than learning new control policies for each new task, it is possi...
read it
-
Neural Task Programming: Learning to Generalize Across Hierarchical Tasks
In this work, we propose a novel robot learning framework called Neural ...
read it
-
DeformNet: Free-Form Deformation Network for 3D Shape Reconstruction from a Single Image
3D reconstruction from a single image is a key problem in multiple appli...
read it
-
Weakly supervised 3D Reconstruction with Adversarial Constraint
Supervised 3D reconstruction has witnessed a significant progress throug...
read it