b'Animesh Garg'

Centralized Model and Exploration Policy for Multi-Agent RL

Reinforcement learning (RL) in partially observable, fully cooperative m...
07/14/2021 ∙ by Qizhen Zhang, et al. ∙ 0 ∙ share

read it
A Persistent Spatial Semantic Representation for High-level Natural Language Instruction Execution

Natural language provides an accessible and expressive interface to spec...
07/12/2021 ∙ by Valts Blukis, et al. ∙ 18 ∙ share

read it
Learning Latent Actions to Control Assistive Robots

Assistive robot arms enable people with disabilities to conduct everyday...
07/06/2021 ∙ by Dylan P. Losey, et al. ∙ 0 ∙ share

read it
GIFT: Generalizable Interaction-aware Functional Tool Affordances without Labels

Tool use requires reasoning about the fit between an object's affordance...
06/28/2021 ∙ by Dylan Turpin, et al. ∙ 0 ∙ share

read it
Neural Hybrid Automata: Learning Dynamics with Multiple Modes and Stochastic Transitions

Effective control and prediction of dynamical systems often require appr...
06/08/2021 ∙ by Michael Poli, et al. ∙ 0 ∙ share

read it
Tesseract: Tensorised Actors for Multi-Agent Reinforcement Learning

Reinforcement Learning in large action spaces is a challenging problem. ...
05/31/2021 ∙ by Anuj Mahajan, et al. ∙ 33 ∙ share

read it
DiSECt: A Differentiable Simulation Engine for Autonomous Robotic Cutting

Robotic cutting of soft materials is critical for applications such as f...
05/25/2021 ∙ by Eric Heiden, et al. ∙ 0 ∙ share

read it
Robust Value Iteration for Continuous Control Tasks

When transferring a control policy from simulation to a physical system,...
05/25/2021 ∙ by Michael Lutter, et al. ∙ 2 ∙ share

read it
Coach-Player Multi-Agent Reinforcement Learning for Dynamic Team Composition

In real-world multiagent systems, agents with different capabilities may...
05/18/2021 ∙ by Bo Liu, et al. ∙ 1 ∙ share

read it
Principled Exploration via Optimistic Bootstrapping and Backward Induction

One principled approach for provably efficient exploration is incorporat...
05/13/2021 ∙ by Chenjia Bai, et al. ∙ 3 ∙ share

read it
Value Iteration in Continuous Actions, States and Time

Classical value iteration approaches are not applicable to environments ...
05/10/2021 ∙ by Michael Lutter, et al. ∙ 4 ∙ share

read it
GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model

Model-free reinforcement learning (RL) for legged locomotion commonly re...
04/20/2021 ∙ by Zhaoming Xie, et al. ∙ 6 ∙ share

read it
LASER: Learning a Latent Action Space for Efficient Reinforcement Learning

The process of learning a manipulation task depends strongly on the acti...
03/29/2021 ∙ by Arthur Allshire, et al. ∙ 0 ∙ share

read it
Articulated Object Interaction in Unknown Scenes with Whole-Body Mobile Manipulation

A kitchen assistant needs to operate human-scale objects, such as cabine...
03/18/2021 ∙ by Mayank Mittal, et al. ∙ 6 ∙ share

read it
S4RL: Surprisingly Simple Self-Supervision for Offline Reinforcement Learning

Offline reinforcement learning proposes to learn policies from large col...
03/10/2021 ∙ by Samarth Sinha, et al. ∙ 0 ∙ share

read it
Learning by Watching: Physical Imitation of Manipulation Skills from Human Videos

We present an approach for physical imitation from human videos for robo...
01/18/2021 ∙ by Haoyu Xiong, et al. ∙ 7 ∙ share

read it
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects

Evolution in nature illustrates that the creatures' biological structure...
12/22/2020 ∙ by Xinlei Pan, et al. ∙ 0 ∙ share

read it
Skill Transfer via Partially Amortized Hierarchical Planning

To quickly solve new tasks in complex environments, intelligent agents n...
11/27/2020 ∙ by Kevin Xie, et al. ∙ 0 ∙ share

read it
C-Learning: Horizon-Aware Cumulative Accessibility Estimation

Multi-goal reaching is an important problem in reinforcement learning ne...
11/24/2020 ∙ by Panteha Naderian, et al. ∙ 0 ∙ share

read it
Action Concept Grounding Network for Semantically-Consistent Video Generation

Recent works in self-supervised video prediction have mainly focused on ...
11/23/2020 ∙ by Wei Yu, et al. ∙ 8 ∙ share

read it
Solving Physics Puzzles by Reasoning about Paths

We propose a new deep learning model for goal-driven tasks that require ...
11/14/2020 ∙ by Augustin Harter, et al. ∙ 0 ∙ share

read it
Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion

Understanding the gap between simulation andreality is critical for rein...
11/04/2020 ∙ by Zhaoming Xie, et al. ∙ 0 ∙ share

read it
Conservative Safety Critics for Exploration

Safe exploration presents a major challenge in reinforcement learning (R...
10/27/2020 ∙ by Homanga Bharadhwaj, et al. ∙ 0 ∙ share

read it
D2RL: Deep Dense Architectures in Reinforcement Learning

While improvements in deep learning architectures have played a crucial ...
10/19/2020 ∙ by Samarth Sinha, et al. ∙ 0 ∙ share

read it
Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion

We present a hierarchical framework that combines model-based control an...
09/21/2020 ∙ by Xingye Da, et al. ∙ 0 ∙ share

read it
OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation

Real-world tasks often exhibit a compositional structure that contains a...
08/17/2020 ∙ by Hongyu Ren, et al. ∙ 1 ∙ share

read it
Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter

When searching for objects in cluttered environments, it is often necess...
08/13/2020 ∙ by Andrey Kurenkov, et al. ∙ 4 ∙ share

read it
Counterfactual Data Augmentation using Locally Factored Dynamics

Many dynamic processes, including common scenarios in robotic control an...
07/06/2020 ∙ by Silviu Pitis, et al. ∙ 0 ∙ share

read it
Causal Discovery in Physical Systems from Videos

Causal discovery is at the core of human cognition. It enables us to rea...
07/01/2020 ∙ by Yunzhu Li, et al. ∙ 0 ∙ share

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...
07/01/2020 ∙ by Homanga Bharadhwaj, et al. ∙ 0 ∙ share

read it
Maximum Entropy Models for Fast Adaptation

Deep Neural Networks have shown great promise on a variety of downstream...
06/30/2020 ∙ by Samarth Sinha, et al. ∙ 12 ∙ share

read it
Experience Replay with Likelihood-free Importance Weights

The use of past experiences to accelerate temporal difference (TD) learn...
06/23/2020 ∙ by Samarth Sinha, et al. ∙ 12 ∙ share

read it
LEAF: Latent Exploration Along the Frontier

Self-supervised goal proposal and reaching is a key component for explor...
05/21/2020 ∙ by Homanga Bharadhwaj, et al. ∙ 0 ∙ share

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...
05/21/2020 ∙ by Homanga Bharadhwaj, et al. ∙ 0 ∙ share

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...
05/21/2020 ∙ by Michelle A. Lee, et al. ∙ 33 ∙ share

read it
DIBS: Diversity inducing Information Bottleneck in Model Ensembles

Although deep learning models have achieved state-of-the-art performance...
03/10/2020 ∙ by Samarth Sinha, et al. ∙ 7 ∙ share

read it
Semi-Supervised StyleGAN for Disentanglement Learning

Disentanglement learning is crucial for obtaining disentangled represent...
03/06/2020 ∙ by Weili Nie, et al. ∙ 24 ∙ share

read it
Curriculum By Texture

Convolutional Neural Networks (CNNs) have shown impressive performance i...
03/03/2020 ∙ by Samarth Sinha, et al. ∙ 5 ∙ share

read it
Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos

Unsupervised landmark learning is the task of learning semantic keypoint...
01/26/2020 ∙ by Aysegul Dundar, et al. ∙ 25 ∙ share

read it
InfoCNF: An Efficient Conditional Continuous Normalizing Flow with Adaptive Solvers

Continuous Normalizing Flows (CNFs) have emerged as promising deep gener...
12/09/2019 ∙ by Tan M. Nguyen, et al. ∙ 33 ∙ share

read it
Motion Reasoning for Goal-Based Imitation Learning

We address goal-based imitation learning, where the aim is to output the...
11/13/2019 ∙ by De-An Huang, et al. ∙ 105 ∙ share

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...
11/13/2019 ∙ by Ajay Mandlekar, et al. ∙ 108 ∙ share

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...
11/11/2019 ∙ by Ajay Mandlekar, et al. ∙ 0 ∙ share

read it
A Programmable Approach to Model Compression

Deep neural networks frequently contain far more weights, represented at...
11/06/2019 ∙ by Vinu Joseph, et al. ∙ 14 ∙ share

read it
Dynamics Learning with Cascaded Variational Inference for Multi-Step Manipulation

The fundamental challenge of planning for multi-step manipulation is to ...
10/29/2019 ∙ by Kuan Fang, et al. ∙ 10 ∙ share

read it
Controlling Assistive Robots with Learned Latent Actions

Assistive robots enable users with disabilities to perform everyday task...
09/20/2019 ∙ by Dylan P. Losey, et al. ∙ 0 ∙ share

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...
09/09/2019 ∙ by Andrey Kurenkov, et al. ∙ 7 ∙ share

read it
Video Interpolation and Prediction with Unsupervised Landmarks

Prediction and interpolation for long-range video data involves the comp...
09/06/2019 ∙ by Kevin J. Shih, et al. ∙ 1 ∙ share

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...
08/16/2019 ∙ by De-An Huang, et al. ∙ 3 ∙ share

read it
Making Sense of Vision and Touch: Learning Multimodal Representations for Contact-Rich Tasks

Contact-rich manipulation tasks in unstructured environments often requi...
07/28/2019 ∙ by Michelle A. Lee, et al. ∙ 0 ∙ share

read it

Animesh Garg

Featured Co-authors