Dipendra Kumar Misra

发表

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

Yoav Artzi, Noah Snavely, Howard Chen, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Tell me Dave: Context-sensitive grounding of natural language to manipulation instructions

Ashutosh Saxena, Jaeyong Sung, Dipendra Kumar Misra, 2014, Int. J. Robotics Res..

Neural Shift-Reduce CCG Semantic Parsing

Yoav Artzi, Dipendra Kumar Misra, 2016, EMNLP.

Tell me Dave: Context-sensitive grounding of natural language to manipulation instructions

Kevin Lee, Ashutosh Saxena, Jaeyong Sung, 2014, Int. J. Robotics Res..

RoboBrain: Large-Scale Knowledge Engine for Robots pdf

Hema Swetha Koppula, Ashutosh Saxena, Ozan Sener, 2014, ArXiv.

Mapping Navigation Instructions to Continuous Control Actions with Position-Visitation Prediction

Ross A. Knepper, Yoav Artzi, Valts Blukis, 2018, CoRL.

CHALET: Cornell House Agent Learning Environment pdf

Andrew Bennett, Yonatan Bisk, Yoav Artzi, 2018, ArXiv.

EARLY FUSION for Goal Directed Robotic Vision

Yejin Choi, Dieter Fox, Yonatan Bisk, 2018, 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning

John Langford, Yoav Artzi, Dipendra Kumar Misra, 2017, EMNLP.

Environment-Driven Lexicon Induction for High-Level Instructions

Ashutosh Saxena, Percy Liang, Dipendra Kumar Misra, 2015, ACL.

Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction

Andrew Bennett, Yoav Artzi, Eyvind Niklasson, 2018, EMNLP.

Sample-Efficient Reinforcement Learning in the Presence of Exogenous Information

Dylan J. Foster, Dipendra Kumar Misra, J. Langford, 2022, COLT.

MULTISTEP INVERSE DYNAMICS

Dipendra Kumar Misra, J. Langford, A. Krishnamurthy, 2022 .

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Dipendra Kumar Misra, J. Langford, Riashat Islam, 2022, ArXiv.

Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning

Akshay Krishnamurthy, Dipendra Misra, Mikael Henaff, 2019, ICML.

Guaranteed Discovery of Control-Endogenous Latent States with Multi-Step Inverse Models

Dylan J. Foster, Dipendra Kumar Misra, J. Langford, 2022, Trans. Mach. Learn. Res..

Lipschitz Continuity in Model-based Reinforcement Learning

Kavosh Asadi, Dipendra Misra, Michael L. Littman, 2018, ICML.

Understanding Contrastive Learning Requires Incorporating Inductive Biases

Dipendra Kumar Misra, S. Kakade, A. Krishnamurthy, 2022, ICML.

Investigating the Role of Negatives in Contrastive Representation Learning pdf

Akshay Krishnamurthy, Jordan T. Ash, Dipendra Kumar Misra, 2021, AISTATS.

Towards a Simple Approach to Multi-step Model-based Reinforcement Learning pdf

Kavosh Asadi, Evan Cater, Dipendra Misra, 2018, ArXiv.

Learning to Generate Better Than Your LLM

Dipendra Kumar Misra, Wen Sun, Kianté Brantley, 2023, ArXiv.

Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning

Kavosh Asadi, Evan Cater, Dipendra Misra, 2018, ArXiv.

Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning pdf

Kavosh Asadi, Evan Cater, Dipendra Misra, 2018, ArXiv.

Survival Instinct in Offline Reinforcement Learning

Dipendra Kumar Misra, A. Kolobov, Anqi Li, 2023, NeurIPS.

Provable Safe Reinforcement Learning with Binary Feedback

Dipendra Kumar Misra, Nathan Kallus, Andrew Bennett, 2022, AISTATS.

Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations pdf

Ming-Wei Chang, Dipendra Misra, Xiaodong He, 2018, EMNLP.

Combating the Compounding-Error Problem with a Multi-step Model pdf

Kavosh Asadi, Dipendra Misra, Seungchan Kim, 2019, ArXiv.

Provably Filtering Exogenous Distractors using Multistep Inverse Dynamics

Dipendra Kumar Misra, J. Langford, A. Krishnamurthy, 2022, International Conference on Learning Representations.

Towards Data-Driven Offline Simulations for Online Reinforcement Learning

Dipendra Kumar Misra, J. Langford, Alex Lamb, 2022, ArXiv.

Principled Offline RL in the Presence of Rich Exogenous Information

Dipendra Kumar Misra, J. Langford, Riashat Islam, 2022, ICML.

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information

Dipendra Kumar Misra, J. Langford, Riashat Islam, 2022, ArXiv.

TOUCHDOWN: Natural Language Navigation and Spatial Reasoning in Visual Street Environments

Dipendra Kumar Misra, Noah Snavely, Yoav Artzi, 2018, 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR).

Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models

Dylan J. Foster, Dipendra Kumar Misra, J. Langford, 2022, arXiv.org.

Towards Principled Representation Learning from Videos for Reinforcement Learning

Dipendra Kumar Misra, Akanksha Saran, John Langford, 2024, ArXiv.

Goal-oriented Vision-and-Dialog Navigation through Reinforcement Learning

Marlos C. Machado, Dipendra Kumar Misra, T. Kollar, 2022 .