254 citations · 1.4k across the 100 of their papers we have counts for
22 papers · 1 filter
Emergent Hand Morphology and Control from Optimizing Robust Grasps of Diverse Objects
Xinlei Pan, Animesh Garg, Animashree Anandkumar +1
Evolution in nature illustrates that the creatures' biological structure and their sensorimotor skills adapt to the environmental changes for survival. Likewise, the ability to mor…
D2RL: Deep Dense Architectures in Reinforcement Learning
Samarth Sinha, Homanga Bharadhwaj, Aravind Srinivas +1
While improvements in deep learning architectures have played a crucial role in improving the state of supervised and unsupervised learning in computer vision and natural language…
Solving Physics Puzzles by Reasoning about Paths
Augustin Harter, Andrew Melnik, Gaurav Kumar +3
We propose a new deep learning model for goal-driven tasks that require intuitive physical reasoning and intervention in the scene to achieve a desired end goal. Its modular struct…
Latent Skill Planning for Exploration and Transfer
Kevin Xie, Homanga Bharadhwaj, Danijar Hafner +2
To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environm…
C-Learning: Horizon-Aware Cumulative Accessibility Estimation
Panteha Naderian, Gabriel Loaiza-Ganem, Harry J. Braviner +4
Multi-goal reaching is an important problem in reinforcement learning needed to achieve algorithmic generalization. Despite recent advances in this field, current algorithms suffer…
Modular Action Concept Grounding in Semantic Video Prediction
Wei Yu, Wenxin Chen, Songhenh Yin +2
Recent works in video prediction have mainly focused on passive forecasting and low-level action-conditional prediction, which sidesteps the learning of interaction between agents…
Dynamics Randomization Revisited:A Case Study for Quadrupedal Locomotion
Zhaoming Xie, Xingye Da, Michiel van de Panne +2
Understanding the gap between simulation and reality is critical for reinforcement learning with legged robots, which are largely trained in simulation. However, recent work has re…
Conservative Safety Critics for Exploration
Homanga Bharadhwaj, Aviral Kumar, Nicholas Rhinehart +3
Safe exploration presents a major challenge in reinforcement learning (RL): when active data collection requires deploying partially trained policies, we must ensure that these pol…
Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion
Xingye Da, Zhaoming Xie, David Hoeller +5
We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago). The sy…
OCEAN: Online Task Inference for Compositional Tasks with Context Adaptation
Hongyu Ren, Yuke Zhu, Jure Leskovec +2
Real-world tasks often exhibit a compositional structure that contains a sequence of simpler sub-tasks. For instance, opening a door requires reaching, grasping, rotating, and pull…
Visuomotor Mechanical Search: Learning to Retrieve Target Objects in Clutter
Andrey Kurenkov, Joseph Taglic, Rohun Kulkarni +4
When searching for objects in cluttered environments, it is often necessary to perform complex interactions in order to move occluding objects out of the way and fully reveal the o…
Counterfactual Data Augmentation using Locally Factored Dynamics
Silviu Pitis, Elliot Creager, Animesh Garg
Many dynamic processes, including common scenarios in robotic control and reinforcement learning (RL), involve a set of interacting subprocesses. Though the subprocesses are not in…
Causal Discovery in Physical Systems from Videos
Yunzhu Li, Antonio Torralba, Animashree Anandkumar +2
Causal discovery is at the core of human cognition. It enables us to reason about the environment and make counterfactual predictions about unseen scenarios that can vastly differ…
De-anonymization of authors through arXiv submissions during double-blind review
Homanga Bharadhwaj, Dylan Turpin, Animesh Garg +1
In this paper, we investigate the effects of releasing arXiv preprints of papers that are undergoing a double-blind review process. In particular, we ask the following research que…
Experience Replay with Likelihood-free Importance Weights
Samarth Sinha, Jiaming Song, Animesh Garg +1
The use of past experiences to accelerate temporal difference (TD) learning of value functions, or experience replay, is a key component in deep reinforcement learning. Prioritizat…
Uniform Priors for Data-Efficient Transfer
Samarth Sinha, Karsten Roth, Anirudh Goyal +3
Deep Neural Networks have shown great promise on a variety of downstream applications; but their ability to adapt and generalize to new data and tasks remains a challenge. However,…
Guided Uncertainty-Aware Policy Optimization: Combining Learning and Model-Based Strategies for Sample-Efficient Policy Learning
Michelle A. Lee, Carlos Florensa, Jonathan Tremblay +4
Traditional robotic approaches rely on an accurate model of the environment, a detailed description of how to perform the task, and a robust perception system to keep track of the…
LEAF: Latent Exploration Along the Frontier
Homanga Bharadhwaj, Animesh Garg, Florian Shkurti
Self-supervised goal proposal and reaching is a key component for exploration and efficient policy learning algorithms. Such a self-supervised approach without access to any oracle…
Diversity inducing Information Bottleneck in Model Ensembles
Samarth Sinha, Homanga Bharadhwaj, Anirudh Goyal +3
Although deep learning models have achieved state-of-the-art performance on a number of vision tasks, generalization over high dimensional multi-modal data, and reliable predictive…
Semi-Supervised StyleGAN for Disentanglement Learning
Weili Nie, Tero Karras, Animesh Garg +4
Disentanglement learning is crucial for obtaining disentangled representations and controllable generation. Current disentanglement methods face several inherent limitations: diffi…
Curriculum By Smoothing
Samarth Sinha, Animesh Garg, Hugo Larochelle
Convolutional Neural Networks (CNNs) have shown impressive performance in computer vision tasks such as image classification, detection, and segmentation. Moreover, recent work in…
Unsupervised Disentanglement of Pose, Appearance and Background from Images and Videos
Aysegul Dundar, Kevin J. Shih, Animesh Garg +3
Unsupervised landmark learning is the task of learning semantic keypoint-like representations without the use of expensive input keypoint-level annotations. A popular approach is t…