Publications

Journal Publications

Integrated Task and Motion Planning
Caelan Reed Garrett, Rohan Chitnis, Rachel Holladay, Beomjoon Kim, Tom Silver, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the Annual Review of Control, Robotics, and Autonomous Systems, Volume 4, May 2021.
PDF / arXiv

Conference Publications

IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
Rohan Chitnis*, Yingchen Xu*, Bobak Hashemi, Lucas Lehnert, Urun Dogan, Zheqing Zhu, Olivier Delalleau.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2024. Yokohama, Japan.
PDF forthcoming / arXiv / Website

Score Models for Offline Goal-Conditioned Reinforcement Learning
Harshit Sikchi, Rohan Chitnis, Ahmed Touati, Alborz Geramifard, Amy Zhang, Scott Niekum.
In the proceedings of the International Conference on Learning Representations (ICLR), 2024. Vienna, Austria.
PDF forthcoming / arXiv

Decision Transformer is a Robust Contender for Offline Reinforcement Learning
Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard, Shagun Sodhani, Amy Zhang.
In the proceedings of the International Conference on Learning Representations (ICLR), 2024. Vienna, Austria.
PDF forthcoming / arXiv

Learning Efficient Abstract Planning Models that Choose What to Predict
Nishanth Kumar, Willie McClinton, Rohan Chitnis, Tom Silver, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
In the proceedings of the Conference on Robot Learning (CoRL), 2023. Atlanta, USA.
PDF / arXiv

Predicate Invention for Bilevel Planning
Tom Silver*, Rohan Chitnis*, Nishanth Kumar, Willie McClinton, Tomás Lozano-Pérez, Leslie Pack Kaelbling, Joshua Tenenbaum.
In the proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2023. Washington DC, USA.
Preliminary version presented at the Multi-disciplinary Conference on Reinforcement Learning and Decision Making (RLDM), 2022.
PDF / arXiv / Code

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
Rohan Chitnis*, Tom Silver*, Joshua Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2022. Kyoto, Japan.
PDF / Video / arXiv

Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
Clement Gehring*, Masataro Asai*, Rohan Chitnis, Tom Silver, Leslie Pack Kaelbling, Shirin Sohrabi, Michael Katz.
In the proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), 2022. Virtual.
PDF / arXiv

Towards Optimal Correlational Object Search
Kaiyu Zheng, Rohan Chitnis, Yoonchang Sung, George Konidaris, Stefanie Tellex.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2022. Philadelphia, USA.
PDF / Video / arXiv

Learning Symbolic Operators for Task and Motion Planning
Tom Silver*, Rohan Chitnis*, Joshua Tenenbaum, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2021. Virtual.
Finalist for Best Paper Award (one of 5 finalists).
PDF / Video / arXiv

GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling
Rohan Chitnis*, Tom Silver*, Joshua Tenenbaum, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021. Virtual.
PDF / Video / arXiv

Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
Tom Silver*, Rohan Chitnis*, Aidan Curtis, Joshua Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
In the proceedings of the AAAI Conference on Artificial Intelligence (AAAI), 2021. Virtual.
PDF / Video / arXiv

CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs
Rohan Chitnis*, Tom Silver*, Beomjoon Kim, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the Conference on Robot Learning (CoRL), 2020. Virtual.
Plenary talk (top 12% of accepted papers).
PDF / Video / arXiv

Efficient Bimanual Manipulation Using Learned Task Schemas
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2020. Virtual.
PDF / Video / arXiv

Intrinsic Motivation for Encouraging Synergistic Behavior
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta, Abhinav Gupta.
In the proceedings of the International Conference on Learning Representations (ICLR), 2020. Virtual.
PDF / OpenReview / Website / arXiv

Evaluating Peer Coaching in an Engineering Communication Lab: A Quantitative Assessment of Students’ Revision Processes
Lisa Volpatti, Alex Hanson, Jennifer Schall, Jesse Dunietz, Amanda Chen, Rohan Chitnis, Eric J. Alm, Alison F. Takemura, Diana M. Chien.
In the proceedings of the American Society for Engineering Education Annual Conference (ASEE), 2020. Montreal, Canada.
PDF

Learning Compact Models for Planning with Exogenous Processes
Rohan Chitnis, Tomás Lozano-Pérez.
In the proceedings of the Conference on Robot Learning (CoRL), 2019. Osaka, Japan.
PDF / Video / arXiv

Learning Quickly to Plan Quickly Using Modular Meta-Learning
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2019. Montreal, Canada.
PDF / Video / arXiv

Learning What Information to Give in Partially Observed Domains
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the Conference on Robot Learning (CoRL), 2018. Zürich, Switzerland.
PDF / Video / arXiv

Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2018. Madrid, Spain.
PDF / Video / arXiv

Finding Frequent Entities in Continuous Data
Ferran Alet, Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
In the proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), 2018. Stockholm, Sweden.
PDF / Website / arXiv

Sequential Quadratic Programming for Task Plan Optimization
Dylan Hadfield-Menell, Christopher Lin, Rohan Chitnis, Stuart Russell, Pieter Abbeel.
In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2016. Daejeon, Korea.
PDF

Guided Search for Task and Motion Plans Using Learned Heuristics
Rohan Chitnis, Dylan Hadfield-Menell, Abhishek Gupta, Siddharth Srivastava, Edward Groshev, Christopher Lin, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2016. Stockholm, Sweden.
PDF / Video

Variable-Length Word Encodings for Neural Translation Models
Rohan Chitnis, John DeNero.
In the proceedings of the Conference on Empirical Methods in Natural Language Processing (EMNLP), 2015. Lisbon, Portugal.
PDF

Modular Task and Motion Planning in Belief Space
Dylan Hadfield-Menell, Edward Groshev, Rohan Chitnis, Pieter Abbeel.
In the proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2015. Hamburg, Germany.
PDF

Combined Task and Motion Planning Through an Extensible Planner-Independent Interface Layer
Siddharth Srivastava, Eugene Fang, Lorenzo Riano, Rohan Chitnis, Stuart Russell, Pieter Abbeel.
In the proceedings of the IEEE International Conference on Robotics and Automation (ICRA), 2014. Hong Kong.
PDF / Website

Workshop Papers

Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
Rohan Chitnis*, Tom Silver*, Joshua Tenenbaum, Tomás Lozano-Pérez, Leslie Pack Kaelbling.
Presented at the AAAI Workshop on Combining Learning and Reasoning (CLeaR), 2022.
PDF

PDDLGym: Gym Environments from PDDL Problems
Tom Silver, Rohan Chitnis.
Presented at the ICAPS Workshop on Bridging the Gap Between AI Planning and Reinforcement Learning (PRL), 2020.
PDF / arXiv

A Unifying Framework for Social Motivation in Human-Robot Interaction
Audrey Wang*, Rohan Chitnis*, Michelle Li*, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
Presented at the AAAI Workshop on Plan, Activity, and Intent Recognition (PAIR), 2020.
PDF

Learning Skill Hierarchies from Predicate Descriptions and Self-Supervision
Tom Silver*, Rohan Chitnis*, Anurag Ajay, Josh Tenenbaum, Leslie Pack Kaelbling.
Presented at the AAAI Workshop on Generalization in Planning (GenPlan), 2020.
PDF

Learning to Plan Under Variable Assistance
Rohan Chitnis*, Jessica Yu*, Lilian Luong, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
Presented at the ICRA Workshop on Robot Teammates Operating in Dynamic, Unstructured Environments (RT-DUNE), 2019.
PDF

Planning to Give Information in Partially Observed Domains with a Learned Weighted Entropy Model
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
Presented at the ICML / IJCAI / AAMAS Workshop on Planning and Learning (PAL), 2018.
PDF / arXiv

Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez.
Presented at the ICML / IJCAI / AAMAS Workshop on Statistical Relational AI (StarAI), 2018.
Winner of Best Paper Award.
PDF / arXiv

Learning an Interface to Improve Efficiency in Combined Task and Motion Planning
Rohan Chitnis, Dylan Hadfield-Menell, Siddharth Srivastava, Abhishek Gupta, Pieter Abbeel.
Presented at the IROS Workshop on Machine Learning in Planning and Control of Robot Motion (MLPC), 2015.
PDF