10 citations · 39 across the 18 of their papers we have counts for
22 papers
Sequential Decision-Making for Inline Text Autocomplete
Rohan Chitnis, Shentao Yang, Alborz Geramifard
Autocomplete suggestions are fundamental to modern text entry systems, with applications in domains such as messaging and email composition. Typically, autocomplete suggestions are…
SMORE: Score Models for Offline Goal-Conditioned Reinforcement Learning
Harshit Sikchi, Rohan Chitnis, Ahmed Touati +3
Offline Goal-Conditioned Reinforcement Learning (GCRL) is tasked with learning to achieve multiple goals in an environment purely from offline datasets using sparse reward function…
IQL-TD-MPC: Implicit Q-Learning for Hierarchical Model Predictive Control
Rohan Chitnis, Yingchen Xu, Bobak Hashemi +4
Model-based reinforcement learning (RL) has shown great promise due to its sample efficiency, but still struggles with long-horizon sparse-reward tasks, especially in offline setti…
When should we prefer Decision Transformers for Offline Reinforcement Learning?
Prajjwal Bhargava, Rohan Chitnis, Alborz Geramifard +2
Offline reinforcement learning (RL) allows agents to learn effective, return-maximizing policies from a static dataset. Three popular algorithms for offline RL are Conservative Q-L…
Learning Efficient Abstract Planning Models that Choose What to Predict
Nishanth Kumar, Willie McClinton, Rohan Chitnis +3
An effective approach to solving long-horizon tasks in robotics domains with continuous state and action spaces is bilevel planning, wherein a high-level search over an abstraction…
Predicate Invention for Bilevel Planning
Tom Silver, Rohan Chitnis, Nishanth Kumar +4
Efficient planning in continuous state and action spaces is fundamentally hard, even when the transition model is deterministic and known. One way to alleviate this challenge is to…
Towards Optimal Correlational Object Search
Kaiyu Zheng, Rohan Chitnis, Yoonchang Sung +2
In realistic applications of object search, robots will need to locate target objects in complex environments while coping with unreliable sensors, especially for small or hard-to-…
Reinforcement Learning for Classical Planning: Viewing Heuristics as Dense Reward Generators
Clement Gehring, Masataro Asai, Rohan Chitnis +4
Recent advances in reinforcement learning (RL) have led to a growing interest in applying RL to classical planning domains or applying classical planning methods to some complex RL…
Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning
Rohan Chitnis, Tom Silver, Joshua B. Tenenbaum +2
In robotic domains, learning and planning are complicated by continuous state spaces, continuous action spaces, and long task horizons. In this work, we address these challenges wi…
Learning Symbolic Operators for Task and Motion Planning
Tom Silver, Rohan Chitnis, Joshua Tenenbaum +2
Robotic planning problems in hybrid state and action spaces can be solved by integrated task and motion planners (TAMP) that handle the complex interaction between motion-level dec…
Integrated Task and Motion Planning
Caelan Reed Garrett, Rohan Chitnis, Rachel Holladay +4
The problem of planning for a robot that operates in environments containing a large number of objects, taking actions to move itself through the world as well as to change the sta…
Planning with Learned Object Importance in Large Problem Instances using Graph Neural Networks
Tom Silver, Rohan Chitnis, Aidan Curtis +3
Real-world planning problems often involve hundreds or even thousands of objects, straining the limits of modern planners. In this work, we address this challenge by learning to pr…
CAMPs: Learning Context-Specific Abstractions for Efficient Planning in Factored MDPs
Rohan Chitnis, Tom Silver, Beomjoon Kim +2
Meta-planning, or learning to guide planning from experience, is a promising approach to improving the computational cost of planning. A general meta-planning strategy is to learn…
Intrinsic Motivation for Encouraging Synergistic Behavior
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta +1
We study the role of intrinsic motivation as an exploration bias for reinforcement learning in sparse-reward synergistic tasks, which are tasks where multiple agents must work toge…
PDDLGym: Gym Environments from PDDL Problems
Tom Silver, Rohan Chitnis
We present PDDLGym, a framework that automatically constructs OpenAI Gym environments from PDDL domains and problems. Observations and actions in PDDLGym are relational, making the…
GLIB: Efficient Exploration for Relational Model-Based Reinforcement Learning via Goal-Literal Babbling
Rohan Chitnis, Tom Silver, Joshua Tenenbaum +2
We address the problem of efficient exploration for transition model learning in the relational model-based reinforcement learning setting without extrinsic goals or rewards. Inspi…
Learning Compact Models for Planning with Exogenous Processes
Rohan Chitnis, Tomás Lozano-Pérez
We address the problem of approximate model minimization for MDPs in which the state is partitioned into endogenous and (much larger) exogenous components. An exogenous state varia…
Efficient Bimanual Manipulation Using Learned Task Schemas
Rohan Chitnis, Shubham Tulsiani, Saurabh Gupta +1
We address the problem of effectively composing skills to solve sparse-reward tasks in the real world. Given a set of parameterized skills (such as exerting a force or doing a top…
Learning Quickly to Plan Quickly Using Modular Meta-Learning
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez
Multi-object manipulation problems in continuous state and action spaces can be solved by planners that search over sampled values for the continuous parameters of operators. The e…
Finding Frequent Entities in Continuous Data
Ferran Alet, Rohan Chitnis, Leslie P. Kaelbling +1
In many applications that involve processing high-dimensional data, it is important to identify a small set of entities that account for a significant fraction of detections. Rathe…
Learning What Information to Give in Partially Observed Domains
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez
In many robotic applications, an autonomous agent must act within and explore a partially observed environment that is unobserved by its human teammate. We consider such a setting…
Integrating Human-Provided Information Into Belief State Representation Using Dynamic Factorization
Rohan Chitnis, Leslie Pack Kaelbling, Tomás Lozano-Pérez
In partially observed environments, it can be useful for a human to provide the robot with declarative information that represents probabilistic relational constraints on propertie…