Dipendra Misra

PhD Candidate,
Department of Computer Science,
Cornell University

Addr: Cornell Tech,
2 W Loop Rd,
New York, NY 10044

Paper on model-based reinforcement learning with Kavosh Asadi and Michael L. Littman accepted at ICML 2018 (arXiv 2018)

I am co-organizing the 3rd Workshop on Representation Learning for NLP (Repl4NLP) at ACL 2018. Consider submitting.

We introduce CHALET a new 3D House simulator from our group. Build on Unity3D with object manipulation support.

Tutorial on Markov Decision Process Theory and Reinforcement Learning [Part 1] [Part 2] [Blog]

Research and Publication

Research Interest: Situated Natural Language Understanding, Semantic Parsing, Dialogue Modelling, Reinforcement learning.

I develop machine learning models for mapping natural language to meaning representations (e.g., Misra and Artzi 2016). I am particularly interested in natural language grounding problems e.g., robot natural language understanding (Misra et al. 2017, 2015a, 2015b, 2014), conversation modeling etc. I am also interested in reinforcement learning theory (Asadi, Misra, Littman 2018).

Here are some awesome people that I have collaborated with: Aaron Walsman, Aditya Jami, Andrew Bennett, Ashesh Jain, Claudia Yan, Evan Carter, Hema S. Koppula, Jaeyong Sung, John Langford, Kavosh Asadi, Kejia Tao, Kevin K. Lee, Michael L. Littman, Ming-Wei Chang, Ozan Sener, Percy Liang, Scott Yih, Xiaodong He, Yoav Artzi, Yonatan Bisk.

ArXiv Preprints

Equivalence Between Wasserstein and Value-Aware Model-based Reinforcement Learning
Kavosh Asadi, Evan Carter, Dipendra Misra and Michael L. Littman
Abstract: We show that the recently proposed value-aware model based reinforcement learning (Farahmand et al. 2017) can be viewed as minimizing the Wasserstein loss when the value function is Lipschitz continuous.
[ArXiv Preprint]


Lipschitz Continuity in Model-based Reinforcement Learning (ICML 2018)
Kavosh Asadi*, Dipendra Misra*, Michael L. Littman (* equal contribution)
Abstract: We provide novel bounds for cascading errors in model-based RL for Lipschitz continuous transition model. We further show the advantage of using Wasserstein metric for measuring distance between transition models and provide experimental and theoretical advantage for controlling Lipschitz constants of deep neural network models.
[ArXiv Preprint]

Mapping Instructions and Visual Observations to Actions with Reinforcement Learning (EMNLP 2017)
Dipendra Misra, John Langford and Yoav Artzi
Abstract: We present an approach for mapping natural language instructions and visual observations to agent actions using reinforcement learning.
[Paper] [Code] [Arxiv Preprint]

Neural Shift-Reduce CCG Semantic Parsing (EMNLP 2016)
Dipendra Misra and Yoav Artzi
Abstract: We present the first published shift-reduce parser for CCG semantic parsing. Our novel learning algorithm considers learning without annotated parse trees, with type constraints and complex categories.
[Paper] [Supplementary] [Code]

Environment-driven lexicon induction for high-level instructions (ACL 2015)
Dipendra K. Misra, Kejia Tao, Percy Liang, Ashutosh Saxena
Punchline: Learning new concepts and meaning of new verbs at test time using environment as an implicit signal.
[Paper] [Supplementary] [Code] [Data] [Simulator] [Bibtex]

Robo Brain: Large-Scale Knowledge Engine for Robots (ISRR 15)
Ashutosh Saxena, Ashesh Jain, Ozan Sener, Aditya Jami, Dipendra K. Misra, Hema S Koppula
Abstract: We introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.
[Paper] [Website] [Bibtex]

Tell Me Dave: Context-Sensitive Grounding of Natural Language to Manipulation Instructions (RSS 2014)
Dipendra K. Misra, Jaeyong Sung, Kevin K. Lee, Ashutosh Saxena
Abstract: Grounding language to actions with application on PR2 robot. Learn from users playing with simulations.
[Paper] [Website] [Simulator] [Bibtex]


Tell Me Dave: Context-Sensitive Grounding of Natural Language to Manipulation Instructions (IJRR 2015)
Dipendra K. Misra, Jaeyong Sung, Kevin K. Lee, Ashutosh Saxena,
[Paper] [Website] [Bibtex]


CHALET: Cornell House Agent Learning Environment (arXiv 2018 report)
Claudia Yan, Dipendra Misra, Andrew Bennett, Aaron Walsman, Yonatan Bisk and Yoav Artzi
Abstract: We introduce a knowledge engine, which learns and shares knowledge representations, for robots to carry out a variety of tasks.
[Paper] [Website] [Bibtex]

Reinforcement Learning for Mapping Instructions to Actions with Reward Learning (NCHRC, AAAI Fall Symposium 2017)
Dipendra K. Misra and Yoav Artzi
Abstract: Learn a reward function directly on images for mapping natural language instructions to actions.
[Paper] [Code]

Bio and Employment


  • Amazon AWS Research Grant (2016)
  • Cornell University Fellowship (2013)
  • 2nd rank in the 2013 graduating B-Tech batch of IIT Kanpur
  • OPJEMS Merit scholarship (2011-12 and 2012-13)
  • Invited to present a lecture in the 2012 Annual Meet of Calcutta Logic Circle celebrating the Alan Turing year
  • Invited to speak at the 10th Indo-German Winter Academy on High Performance Computing
  • Academic Excellence Award (2009-10 and 2010-11)
  • Was ranked 156th in first attempt out of 3,50,000+ students who appeared in JEE 2009
  • Certificate of merit in National Standard Examination in Physics 2007(State Level)


I like spending some time as an amateur pianist (some of my old Chopin recordings- Ballade 1 Op 23 [Part 1/2], Valse Op 64 2, Raindrop Prelude, Valse Op 34 2, Posthumous Valse A minor, Nocturne 20 C# Minor). I am currently experimenting with writing new compositions fusing Indian melodies with western romanticism. I also maintain peripheral interest in politics and philosophy.