Dinesh Jayaraman

research

∙ 05/22/2023

TOM: Learning Policy-Aware Models for Model-Based Reinforcement Learning via Transition Occupancy Matching

Standard model-based reinforcement learning (MBRL) approaches fit a tran...

0 Yecheng Jason Ma, et al. ∙

research

∙ 03/23/2023

Planning Goals for Exploration

Dropped into an unknown environment, what should an agent do to quickly ...

0 Edward S. Hu, et al. ∙

research

∙ 02/16/2023

Learning a Meta-Controller for Dynamic Grasping

Grasping moving objects is a challenging task that combines multiple sub...

0 Yinsen Jia, et al. ∙

research

∙ 12/17/2022

Training Robots to Evaluate Robots: Example-Based Interactive Reward Functions for Policy Learning

Physical interactions can often help reveal information that is not read...

0 Kun Huang, et al. ∙

research

∙ 10/28/2022

Long-HOT: A Modular Hierarchical Approach for Long-Horizon Object Transport

We address key challenges in long-horizon embodied exploration and navig...

0 Dinesh Jayaraman, et al. ∙

research

∙ 09/25/2022

Vision-based Perimeter Defense via Multiview Pose Estimation

Previous studies in the perimeter defense game have largely focused on t...

2 Elijah S. Lee, et al. ∙

research

∙ 06/07/2022

How Far I'll Go: Offline Goal-Conditioned Reinforcement Learning via f-Advantage Regression

Offline goal-conditioned reinforcement learning (GCRL) promises general-...

27 Yecheng Jason Ma, et al. ∙

research

∙ 02/04/2022

SMODICE: Versatile Offline Imitation Learning via State Occupancy Matching

We propose State Matching Offline DIstribution Correction Estimation (SM...

0 Yecheng Jason Ma, et al. ∙

research

∙ 01/19/2022

Prospective Learning: Back to the Future

Research on both natural intelligence (NI) and artificial intelligence (...

8 Joshua T. Vogelstein, et al. ∙

research

∙ 12/14/2021

Conservative and Adaptive Penalty for Model-Based Safe Reinforcement Learning

Reinforcement Learning (RL) agents in the real world must satisfy safety...

0 Yecheng Jason Ma, et al. ∙

research

∙ 08/26/2021

Probabilistic Modeling for Human Mesh Recovery

This paper focuses on the problem of 3D human reconstruction from 2D evi...

5 Nikos Kolotouros, et al. ∙

research

∙ 07/19/2021

Know Thyself: Transferable Visuomotor Control Through Robot-Awareness

Training visuomotor robot controllers from scratch on a new robot typica...

4 Edward S. Hu, et al. ∙

research

∙ 07/12/2021

Conservative Offline Distributional Reinforcement Learning

Many reinforcement learning (RL) problems in practice are offline, learn...

0 Yecheng Jason Ma, et al. ∙

research

∙ 04/02/2021

How Are Learned Perception-Based Controllers Impacted by the Limits of Robust Control?

The difficulty of optimal control problems has classically been characte...

2 Jingxi Xu, et al. ∙

research

∙ 11/30/2020

Diverse Sampling for Normalizing Flow Based Trajectory Forecasting

For autonomous cars to drive safely and effectively, they must anticipat...

0 Yecheng Jason Ma, et al. ∙

research

∙ 10/18/2020

Model-Based Inverse Reinforcement Learning from Visual Demonstrations

Scaling model-based inverse reinforcement learning (IRL) to real robotic...

0 Neha Das, et al. ∙

research

∙ 08/15/2020

Cautious Adaptation For Reinforcement Learning in Safety-Critical Settings

Reinforcement learning (RL) in real-world safety-critical target setting...

7 Jesse Zhang, et al. ∙

research

∙ 06/23/2020

Long-Horizon Visual Planning with Goal-Conditioned Hierarchical Predictors

The ability to predict and plan into the future is fundamental for agent...

8 Karl Pertsch, et al. ∙

research

∙ 05/29/2020

DIGIT: A Novel Design for a Low-Cost Compact High-Resolution Tactile Sensor with Application to In-Hand Manipulation

Despite decades of research, general purpose in-hand manipulation remain...

11 Mike Lambeta, et al. ∙

research

∙ 01/07/2020

An Exploration of Embodied Visual Exploration

Embodied computer vision considers perception for robots in general, uns...

14 Santhosh K. Ramakrishnan, et al. ∙

research

∙ 12/31/2019

Morphology-Agnostic Visual Robotic Control

Existing approaches for visuomotor robotic control typically require cha...

16 Brian Yang, et al. ∙

research

∙ 12/11/2019

SMiRL: Surprise Minimizing RL in Dynamic Environments

All living organisms struggle against the forces of nature to carve out ...

8 Glen Berseth, et al. ∙

research

∙ 06/27/2019

Emergence of Exploratory Look-Around Behaviors through Active Observation Completion

Standard computer vision systems assume access to intelligently captured...

1 Santhosh K. Ramakrishnan, et al. ∙

research

∙ 05/28/2019

Causal Confusion in Imitation Learning

Behavioral cloning reduces policy learning to supervised learning by tra...

0 Pim de Haan, et al. ∙

research

∙ 05/17/2019

REPLAB: A Reproducible Low-Cost Arm Benchmark Platform for Robotic Learning

Standardized evaluation measures have aided in the progress of machine l...

0 Brian Yang, et al. ∙

research

∙ 03/11/2019

Manipulation by Feel: Touch-Based Control with Deep Predictive Models

Touch sensing is widely acknowledged to be important for dexterous robot...

2 Stephen Tian, et al. ∙

research

∙ 08/23/2018

Time-Agnostic Prediction: Predicting Predictable Video Frames

Prediction is arguably one of the most basic functions of an intelligent...

8 Dinesh Jayaraman, et al. ∙

research

∙ 05/28/2018

More Than a Feeling: Learning to Grasp and Regrasp using Vision and Touch

For humans, the process of grasping an object relies heavily on rich tac...

6 Roberto Calandra, et al. ∙

research

∙ 12/07/2016

Pano2Vid: Automatic Cinematography for Watching 360^∘ Videos

We introduce the novel task of Pano2Vid - automatic cinematography in pa...

0 Yu-Chuan Su, et al. ∙

research

∙ 12/01/2016

Object-Centric Representation Learning from Unlabeled Videos

Supervised (pre-)training currently yields state-of-the-art performance ...

0 Ruohan Gao, et al. ∙

research

∙ 06/15/2015

Slow and steady feature analysis: higher order temporal coherence in video

How can unlabeled video augment visual learning? Existing methods perfor...

0 Dinesh Jayaraman, et al. ∙

research

∙ 05/08/2015

Learning image representations tied to ego-motion

Understanding how images of objects and scenes behave in response to spe...

0 Dinesh Jayaraman, et al. ∙

research

∙ 09/15/2014

Zero Shot Recognition with Unreliable Attributes

In principle, zero-shot learning makes it possible to train a recognitio...

0 Dinesh Jayaraman, et al. ∙

Dinesh Jayaraman

Featured Co-authors