Senior Researcher,
Microsoft Research, New York

Dipendra Kumar Misra

I am a machine learning researcher specializing in the field of natural language understanding, interactive learning (e.g., reinforcement learning), and representation learning. My main research agenda is to develop generalizable agents that can interact with the world using actions and natural language, and solve a range of tasks using reward, natural language feedback, or other types of feedback.

News: Our LASER paper got accepted at ICLR 2024, trended on Github python, and got featured in a Verge article!

My research agenda has the following main threads.

  • Interactive Learning (Learning Algorithm): I am interested in developing both practical and efficient algorithms for training agents. In particular, my recent focus has been on developing algorithms for fine-tuning agents such as LLM (arXiv 2023). I am interested in developing algorithms that are provably-efficient, or use insights from theory to solve real-world challenges. My representative work on this agenda includes a list of recent RL algorithms for problems with complex observations that are provably sample-efficient and computationally-efficient: the Homer algorithm (ICML 2020), RichID algorithm (NeurIPS 2020), FactoRL Algorithm (ICLR 2021), and PPE algorithm (ICLR 2022).

  • Language Feedback (Learning Signal): Natural language is an expressive medium for training and controlling agents that can be used by most humans. I am interested in developing agents that can understand and execute instructions in natural language, and also be trained using these mediums. Representative work on this agenda include the EMNLP 2017, EMNLP 2018, CoRL 2018, and CVPR 2019 papers on developing agents that can follow natural language instruction, and our recent Learning from Language Feedback (LLF) Benchmark (arXiv 2023) and the ICML 2021 paper that trains these agents using just natural language.

  • Representation Learning (Model): An agent needs to learn the right representation of the world to make decisions. E.g., a multi-modal LLM may embed image in a certain way to generate an action or caption. This choice of embedding/representation is very important. I am interested in developing the theory and practice of representation learning methods for training these embeddings, specially, using self-supervised learning. Representative work includes our recent paper at ICLR 2024 (Spotlight) for training representations using video data, and AISTATS 2022 and ICML 2022 on understanding the behavior of contrastive learning. I am also interested in understanding representations, and a representative work on this is our recent paper on the LASER method at ICLR 2024 for probing and improving LLM reasoning.

Beyond my main agenda, I also have interest in a diverse range of topics including language and vision problems, semantic parsing, statistical learning theory, and computational social science.

Bio: I am a Senior Researcher at Microsoft Research, New York. I received my PhD in computer science from Cornell University (2019) and my bachelors in computer science from Indian Institute of Technology Kanpur (2013).

Quick Links:   MSR Reinforcement Learning,   Intrepid Code Base,   CIFF Code Base,   Math for AI,   My Blog,   RL Formulas

Publications



New Preprints

Policy Improvement using Language Feedback Models
Victor Zhong, Dipendra Misra, Xingdi Yuan, Marc-Alexandre Côté
[arXiv 2024]

LLF-Bench: Benchmark for Interactive Learning from Language Feedback
Ching-An Cheng, Andrey Kolobov, Dipendra Misra, Allen Nie, Adith Swaminathan (alphabetic ordering)
[arXiv 2023] [Code] [Website]

Learning to Generate Better Than Your LLM
Jonathan D. Chang, Kiante Brantley, Rajkumar Ramamurthy, Dipendra Misra, Wen Sun
[arXiv 2023] [Preliminary Version accepted at NeurIPS 2023 Workshop]



Conference and Journal Papers

Towards Principled Representation Learning from Videos for Reinforcement Learning
Dipendra Misra*, Akanksha Saran*, Tengyang Xie, Alex Lamb, and John Langford (* equal contribution)
In Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024.
[ICLR 2024] [ICLR Spotlight] [Code]

The Truth is in There: Improving Reasoning in Language Models with Layer-Selective Rank Reduction
Pratyusha Sharma, Jordan T. Ash* and Dipendra Misra* (* equal advising)
[This paper presents a surprising discovery that doing low-rank approximation of selective weight matrices of an LLM can boost the LLM's QA performance, at times by 20-30% point.]
In Proceedings of the 12th International Conference on Learning Representations (ICLR), 2024.
[arXiv 2023] [ICLR 2024] [Code] [Website]

Survival Instinct in Offline Reinforcement Learning
Anqi Li, Dipendra Misra, Andrey Kolobov and Ching-An Cheng
In Conference on Neural Information Processing Systems (NeurIPS), 2023
[arXiv 2023] [NeurIPS Spotlight] [Preliminary Version accepted at ICML Workshop]

Agent-Controller Representations: Principled Offline RL with Rich Exogenous Information
Riashat Islam, Manan Tomar, Alex Lamb, Yonathan Efroni, Hongyu Zang, Aniket Didolkar, Dipendra Misra, Xin Li, Harm van Seijen, Remi Tachet des Combes, John Langford
In Proceedings of the International Conference of Machine Learning (ICML), 2023.
[ICML 2023 Version] [Preliminary version accepted at NeurIPS 2022 workshop]

Guaranteed Discovery of Controllable Latent States with Multi-Step Inverse Models
Alex Lamb, Riashat Islam, Yonathan Efroni, Aniket Didolkar, Dipendra Misra, Dylan Foster, Lekan Molu, Rajan Chari, Akshay Krishnamurthy, and John Langford
In Proceedings of the Transactions on Machine Learning Research (TMLR), 2023.
[TMLR 2023 Version] [arXiv 2022] [Website]

Provable Safe Reinforcement Learning with Binary Feedback
Andrew Bennett, Dipendra Misra, and Nathan Kallus
In Proceedings of the 26th International Conference on Artificial Intelligence and Statistics (AISTATS), 2023.
[AISTAS 2023 Version] [arXiv 2022] [Code]

Provably Sample-Efficient RL with Side Information about Latent Dynamics
Yao Liu, Dipendra Misra, Miro Dudík, and Robert Schapire
In Proceedings of the 36th Conference on Neural Information Processing Systems (NeurIPS), 2022.
[NeurIPS 2022 version] [arXiv 2022]

Sample-Efficient RL in the Presence of Exogenous Information
Yonathan Efroni, Dylan Foster, Dipendra Misra, Akshay Krishnamurthy and John Langford
In Proceedings of the 35th Conference on Learning Theory (COLT), 2022.
[COLT Version] [arXiv 2022]

Understanding Contrastive Learning Requires Incorporating Inductive Biases
Nikunj Saunshi, Jordan Ash, Surbhi Goel, Dipendra Misra, Cyril Zhang, Sanjeev Arora, Sham Kakade, Akshay Krishnamurthy
In Proceedings of the 39th International Conference on Machine Learning (ICML), 2022.
[ICML Version] [arXiv 2022]

Provable RL with Exogenous Distractors via Multistep Inverse Dynamics
Yonathan Efroni, Dipendra Misra, Akshay Krishnamurthy, Alekh Agarwal, and John Langford
In Proceedings of the 10th International Conference on Learning Representations (ICLR), 2022.
[ICLR 2022] [arXiv 2021] [Code] [Oral Presentation]

Investigating the Role of Negatives in Contrastive Representation Learning
Jordan Ash, Surbhi Goel, Akshay Krishnamurthy, and Dipendra Misra     (alphabetic ordering)
The 25th International Conference on Artificial Intelligence and Statistics (AISTATS), 2022.
[arXiv 2021] [Code to come soon]

Interactive Learning from Activity Description
Khanh Nguyen, Dipendra Misra, Robert Schapire, Miro Dudík, Patrick Shafto
In Proceedings of the 38th International Conference on Machine Learning (ICML), 2021.
[Paper] [Version at EML workshop, ICLR 2021] [Code]

Provable Rich Observation Reinforcement Learning with Combinatorial Latent States
Dipendra Misra, Qinghua Liu, Chi Jin, John Langford
In Proceedings of the 9th International Conference on Learning Representations (ICLR), 2021.
[Paper] [Code] [RL Theory Seminar]

Learning the Linear Quadratic Regulator from Nonlinear Observations
Zakaria Mhammedi, Dylan J. Foster, Max Simchowitz, Dipendra Misra, Wen Sun, Akshay Krishnamurthy, Alexander Rakhlin, John Langford
In Proceedings of the 34th Conference on Neural Information Processing Systems (NeuRIPS), 2020.
[arXiv Version] [NeuRIPS Version] [Code]

Kinematic State Abstraction and Provably Efficient Rich-Observation Reinforcement Learning
Dipendra Misra, Mikael Henaff, Akshay Krishnamurthy, and John Langford
In Proceedings of the 37th International Conference on Machine Learning (ICML), 2020.
[arXiv Version] [ICML Version] [Code]

Early Fusion for Goal Directed Robotic Vision
Aaron Walsman, Yonatan Bisk, Saadia Gabriel, Dipendra Misra, Yoav Artzi, Yejin Choi, Dieter Fox
In International Conference on Intelligent Robots and Systems (IROS), 2019.
[Paper]    [Robocup Best paper nomination]

Touchdown: Natural Language Navigation and Spatial Reasoning in Visual Street Environments
Howard Chen, Alane Suhr, Dipendra Misra, Noah Snavely, Yoav Artzi
In Conference on Computer Vision and Pattern Recognition (CVPR), 2019.
[Paper] [Dataset and SDR Code] [Navigation Code]

Mapping Navigation Instructions to Continuous Control Actions with Position Visitation Prediction
Valts Blukis, Dipendra Misra, Ross A. Knepper, and Yoav Artzi
In Proceedings of the Conference on Robot Learning (CoRL), 2018.
[Paper] [Code] [Demo Video]

Policy Shaping and Generalized Update Equations for Semantic Parsing from Denotations
Dipendra Misra, Ming-Wei Chang, Xiaodong He and Wen-tau Yih
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
[Paper] [Code]

Mapping Instructions to Actions in 3D Environments with Visual Goal Prediction
Dipendra Misra, Andrew Bennett, Valts Blukis, Eyvind Niklasson, Max Shatkhin, and Yoav Artzi
In Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2018.
[Paper] [Code, Data and Simulators]

Lipschitz Continuity in Model-based Reinforcement Learning
Kavosh Asadi*, Dipendra Misra*, Michael L. Littman (* equal contribution)
In Proceedings of the 35th International Conference on Machine Learning (ICML), 2018.
[Paper] [Code]

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning
Dipendra Misra, John Langford and Yoav Artzi
In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2017.
[Paper] [Code] [Arxiv Preprint]

Neural Shift-Reduce CCG Semantic Parsing
Dipendra Misra and Yoav Artzi
In Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing (EMNLP), 2016.
[Paper] [Supplementary] [Code]

Tell Me Dave: Context-Sensitive Grounding of Natural Language to Manipulation Instructions
Dipendra K. Misra, Jaeyong Sung, Kevin K. Lee, Ashutosh Saxena
In The International Journal of Robotics Research (IJRR), 2015.
[Paper]
(Note the domain tellmedave DOT com no longer belongs to my coauthors and I.
Also, the link tellmedave DOT cs DOT cornell DOT edu is no longer active)

Environment-driven lexicon induction for high-level instructions
Dipendra K. Misra, Kejia Tao, Percy Liang, Ashutosh Saxena
In Proceedings of the Annual Meeting of the Association for Computational Linguistics (ACL), 2015.
[Paper] [Supplementary] [Code] [Data] [Simulator] [Bibtex]

Tell Me Dave: Context-Sensitive Grounding of Natural Language to Manipulation Instructions
Dipendra K. Misra, Jaeyong Sung, Kevin K. Lee, Ashutosh Saxena
In Proceedings of the Robotics: Science and systems (RSS), 2015.
[Paper]
(Note the domain tellmedave DOT com no longer belongs to my coauthors or I.
Also, the link tellmedave DOT cs DOT cornell DOT edu is no longer active)




Workshop

Towards Data-Driven Offline Simulations for Online Reinforcement Learning
Shengpu Tang, Felipe Vieira Frujeri, Dipendra Misra, Alex Lamb, John Langford, Paul Mineiro, Sebastian Kochman
[arXiv 2022] (Accepted at NeurIPS 2022 "3rd Offline RL Workshop: Offline RL as a "Launchpad" Workshop)

Have you tried Neural Topic Models? Comparative Analysis of Neural and Non-Neural Topic Models with Application to COVID-19 Twitter Data
Andrew Benett, Dipendra Misra, and Nga Than     (alphabetic ordering)
Data Science for Social Good (DSSG) workshop at Conference on Knowledge Discovery and Data Mining (KDD) 2021
[arXiv 2021] [Code]

Towards a Simple Approach to Multi-step Model-based Reinforcement Learning
Kavosh Asadi, Evan Carter, Dipendra Misra, Michael Littman
Deep Reinforcement Learning Workshop at the Conference on Neural Information Processing Systems (NeurIPS), 2018.
[Paper]

The Third Workshop on Representation Learning for NLP (Rep4NLP)
Isabelle Augenstein, Kris Cao, He He, Felix Hill, Spandana Gella, Jamie Kiros, Hongyuan Mei and Dipendra Misra
Workshop at the Annual Meeting of the Association for Computational Linguistics (ACL), 2018.
[Workshop Proceedings]

Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning
Kavosh Asadi, Evan Carter, Dipendra Misra and Michael L. Littman
Workshop on Prediction and Generative Modeling in Reinforcement Learning (PGMRL) at the International Conference on Machine Learning (ICML), 2018.
[ArXiv Preprint]

Reinforcement Learning for Mapping Instructions to Actions with Reward Learning
Dipendra Misra and Yoav Artzi
Symposium on Natural Communication for Human-Robot Collaboration at AAAI Fall Symposium Series, 2017.
[Paper] [Code]


Old Preprints

CHALET: Cornell House Agent Learning Environment
Claudia Yan, Dipendra Misra, Andrew Bennett, Aaron Walsman, Yonatan Bisk and Yoav Artzi
arXiv report, 2018.
[Paper] [Code]

Combating the Compounding-Error Problem with a Multi-step Model
Kavosh Asadi, Dipendra Misra, Seungchan Kim, Michel L Littman
arXiv, 2019.
[Paper]

Robo Brain: Large-Scale Knowledge Engine for Robots
Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra K. Misra, Hema S Koppula
[Paper]

Posts

  • Academia and Compute-Intensive AI Research    [Post]

  • PAC with Hoeffding-Bernstein    [Post]

  • Growing Bifurcation of AI Scholarship     [Post]

  • Dynkin’s π-λ Theorem and CDF     [Part 1]     [Part 2]

  • Are Synthetic Datasets in AI Useful?     [Post]

  • Are we doing NLP the right way?     [Post]

  • Writing and Proof Reading Research Code     [Post]

  • Mathematical Analysis of Policy Gradient Methods     [Post]

  • Tutorial on Markov Decision Process Theory and Reinforcement Learning.     [Slides Part 1]     [Slides Part 2]     [Post]