Machine Teaching Group - Publications

2024

Generative AI for Education (GAIED): Advances, Opportunities, and Challenges
P. Denny, S. Gulwani, N. T. Heffernan, T. Käser, S. Moore, A. N. Rafferty, A. Singla
Survey article; addition resources at https://gaied.org/
Benchmarking Generative Models on Computational Thinking Tests in Elementary Visual Programming
V. Pădurean, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) - Track on Datasets and Benchmark, 2024 (to appear)
Hints-In-Browser: Benchmarking Language Models for Programming Feedback Generation
N. Kotalwar, A. Gotovos, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS) - Track on Datasets and Benchmark, 2024 (to appear)
Optimally Teaching a Linear Behavior Cloning Agent
S. K. Bharti, S. Wright, A. Singla, X. Zhu
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2024 (to appear)
Analyzing-Evaluating-Creating: Assessing Computational Thinking and Problem Solving in Visual Programming Domains
A. Ghosh, L. Malva, A. Singla
In Proceedings of Technical Symposium on Computer Science Education (SIGCSE), 2024
Automating Human Tutor-Style Programming Feedback: Leveraging GPT-4 Tutor Model for Hint Generation and GPT-3.5 Student Model for Hint Validation
T. Phung, V. Pădurean, A. Singh, C. Brooks, J. Cambronero, S. Gulwani, A. Singla, G. Soares
In Proceedings of Learning Analytics and Knowledge Conference (LAK), 2024
Neural Task Synthesis for Visual Programming
V. Pădurean, G. Tzannetos, A. Singla
Transactions on Machine Learning Research (TMLR), 2024
Informativeness of Reward Functions in Reinforcement Learning
R. Devidze, P. Kamalaruban, A. Singla
In Proceedings of International Conference on Autonomous Agents & Multiagent Systems (AAMAS), 2024
Large Language Models for In-Context Student Modeling: Synthesizing Student's Behavior in Visual Programming
M. H. Nguyen, S. Tschiatschek, A. Singla
In Proceedings of International Conference on Educational Data Mining (EDM), 2024
Towards Generalizable Agents in Text-Based Educational Environments: A Study of Integrating RL with LLMs
B. Radmehr, A. Singla, T. Käser
In Proceedings of International Conference on Educational Data Mining (EDM), 2024
Proximal Curriculum with Task Correlations for Deep Reinforcement Learning
G. Tzannetos, P. Kamalaruban, A. Singla
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2024
Learning Embeddings for Sequential Tasks Using Population of Agents
M. Mahajan, G. Tzannetos, G. Radanovic, A. Singla
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2024
Reward Model Learning vs. Direct Policy Optimization: A Comparative Analysis of Learning from Human Preferences
A. Nika, D. Mandal, P. Kamalaruban, G. Tzannetos, G. Radanovic, A. Singla
In Proceedings of International Conference on Machine Learning (ICML), 2024
Optimal Decision Making Under Strategic Behavior
S. Tsirtsis, B. Tabibian, M. Khajehnejad, A. Singla, B. Schölkopf, M. Gomez-Rodriguez
Management Science, 2024
Defending Against Unknown Corrupted Agents: Reinforcement Learning of Adversarially Robust Nash Equilibria
A. Nika, J. Nöther, A. Singla, G. Radanovic
Transactions on Machine Learning Research (TMLR), 2024
Task Synthesis for Elementary Visual Programming in XLogoOnline Environment
C. Wen, A. Ghosh, J. Staub, A. Singla
In Proceedings of International Conference on Artificial Intelligence in Education (AIED) Late-Breaking Results Track, 2024
Synthesizing a Progression of Subtasks for Block-Based Visual Programming Tasks
A. Tercan, A. Ghosh, H. F. Eniser, M. Christakis, A. Singla
Workshop on AI for Education (AI4ED) at AAAI, 2024

2023

Generating High-Precision Feedback for Programming Syntax Errors using Large Language Models
T. Phung, J. Cambronero, S. Gulwani, T. Kohn, R. Majumdar, A. Singla, G. Soares
In Proceedings of International Conference on Educational Data Mining (EDM), 2023
Generative AI for Programming Education: Benchmarking ChatGPT, GPT-4, and Human Tutors
T. Phung, V. Pădurean, J. Cambronero, S. Gulwani, T. Kohn, R. Majumdar, A. Singla, G. Soares
In Proceedings of International Computing Education Research V.2 (ICER Poster Track), 2023
Evaluating ChatGPT and GPT-4 for Visual Programming
A. Singla
In Proceedings of International Computing Education Research V.2 (ICER Poster Track), 2023
Proximal Curriculum for Reinforcement Learning Agents
G. Tzannetos, B. G. Ribeiro, P. Kamalaruban, A. Singla
Transactions on Machine Learning Research (TMLR), 2023
Online Reinforcement Learning with Uncertain Episode Lengths
D. Mandal, G. Radanovic, J. Gan, A. Singla, R. Majumdar
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2023
Online Defense Strategies for Reinforcement Learning Against Adaptive Reward Poisoning
A. Nika, A. Singla, G. Radanovic
In Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS), 2023
Implicit Poisoning Attacks in Two-Agent Reinforcement Learning: Adversarial Policies for Training-Time Attacks
M. Mohammadi, J. Nöther, D. Mandal, A. Singla, G. Radanovic
In Proceedings of International Conference on Autonomous Agents & Multiagent Systems (AAMAS), 2023
Specifying and Testing k-Safety Properties for Machine-Learning Models
M. Christakis, H. F. Eniser, J. Hoffmann, A. Singla, V. Wüstholz
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2023
Defense Against Reward Poisoning Attacks in Reinforcement Learning
K. Banihashem, A. Singla, G. Radanovic
Transactions on Machine Learning Research (TMLR), 2023

2022

Exploration-Guided Reward Shaping for Reinforcement Learning under Sparse Rewards
R. Devidze, P. Kamalaruban, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2022
Envy-free Policy Teaching to Multiple Agents
J. Gan, R. Majumdar, G. Radanovic, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2022
On Batch Teaching with Sample Complexity Bounded by VCD
F. Mansouri, H. U. Simon, A. Singla, S. Zilles
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2022
Provable Defense against Backdoor Policies in Reinforcement Learning
S. K. Bharti, X. Zhang, A. Singla, X. Zhu
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2022
Adaptive Scaffolding in Block-based Programming via Synthesizing New Tasks as Pop Quizzes
A. Ghosh, S. Tschiatschek, S. Devlin, A. Singla
In Proceedings of International Conference on Artificial Intelligence in Education (AIED), 2022
From {Solution Synthesis} to {Student Attempt Synthesis} for Block-Based Visual Programming Tasks
A. Singla, N. Theodoropoulos
In Proceedings of International Conference on Educational Data Mining (EDM), 2022
Equity and Fairness of Bayesian Knowledge Tracing
S. Tschiatschek, M. Knobelsdorf, A. Singla
In Proceedings of International Conference on Educational Data Mining (EDM), 2022
Bayesian Persuasion in Sequential Decision-Making
J. Gan, R. Majumdar, G. Radanovic, A. Singla
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2022
(AAAI-22 Outstanding Paper Honorable Mention Award)
Admissible Policy Teaching through Reward Design
K. Banihashem, A. Singla, J. Gan, G. Radanovic
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2022
Sequential Decision Making With Information Asymmetry
J. Gan, R. Majumdar, G. Radanovic, A. Singla
In Proceedings of International Conference on Concurrency Theory (CONCUR), 2022
Learning to Switch Among Agents in a Team via 2-Layer Markov Decision Processes
V. Meresht, A. De, A. Singla, M. Gomez-Rodriguez
Transactions on Machine Learning Research (TMLR), 2022
Actual Causality and Responsibility Attribution in Decentralized Partially Observable Markov Decision Processes
S. Triantafyllou, A. Singla, G. Radanovic
In Proceedings of Conference on Artificial Intelligence, Ethics, and Society (AIES), 2022

2021

Reinforcement Learning for Education: Opportunities and Challenges
A. Singla, A. N. Rafferty, G. Radanovic, N. T. Heffernan
Survey article; addition resources at https://rl4ed.org/
Curriculum Design for Teaching via Demonstrations: Theory and Applications
G. Yengera, R. Devidze, P. Kamalaruban, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2021
Explicable Reward Design for Reinforcement Learning Agents
R. Devidze, G. Radanovic, P. Kamalaruban, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2021
Teaching via Best-Case Counterexamples in the Learning-with-Equivalence-Queries Paradigm
A. Kumar, Y. Chen, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2021
Teaching an Active Learner with Contrastive Examples
C. Wang, A. Singla, Y. Chen
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2021
On Blame Attribution for Accountable Multi-Agent Sequential Decision Making
S. Triantafyllou, A. Singla, G. Radanovic
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2021
Policy Teaching in Reinforcement Learning via Environment Poisoning Attacks
A. Rakhsha, G. Radanovic, R. Devidze, X. Zhu, A. Singla
Journal of Machine Learning Research (JMLR), 2021
The Teaching Dimension of Kernel Perceptron
A. Kumar, H. Zhang, A. Singla, Y. Chen
In Proceedings of International Conference on Artificial Intelligence and Statistics (AISTATS), 2021
Quizzing Policy Using Reinforcement Learning for Inferring the Student Knowledge State
J. He-Yueya, A. Singla
In Proceedings of International Conference on Educational Data Mining (EDM), 2021
The Sample Complexity of Teaching-by-Reinforcement on Q-Learning
X. Zhang, S. K. Bharti, Y. Ma, A. Singla, X. Zhu
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2021
On the Fairness of Time-Critical Influence Maximization in Social Networks
J. Ali, M. Babaei, A. Chakraborty, B. Mirzasoleiman, K. P. Gummadi, A. Singla
Transactions on Knowledge and Data Engineering (TKDE), 2021
Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments
A. Rakhsha*, X. Zhang*, X. Zhu, A. Singla
Workshop on Learning and Decision-Making with Strategic Feedback (StratML) at NeurIPS, 2021
Reinforcement Learning Under Algorithmic Triage
E. Straitouri, A. Singla, V. Meresht, M. Gomez-Rodriguez
Workshop on Cooperative AI at NeurIPS, 2021
Fair Clustering Using Antidote Data
A. Chhabra, A. Singla, P. Mohapatra
Workshop on Algorithmic Fairness through the Lens of Causality and Robustness (AFCR) at NeurIPS, 2021
Fairness Degrading Adversarial Attacks Against Clustering Algorithms
A. Chhabra, A. Singla, P. Mohapatra
Workshop on Algorithmic Fairness through the Lens of Causality and Robustness (AFCR) at NeurIPS, 2021
Average-case Complexity of Teaching Convex Polytopes via Halfspace Queries
A. Kumar, A. Singla, Y. Yue, Y. Chen
arXiv 2006.14677, 2021

2020

Synthesizing Tasks for Block-based Programming
U. Z. Ahmed, M. Christakis, A. Efremov, N. Fernandez, A. Ghosh, A. Roychoudhury, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2020
Task-agnostic Exploration in Reinforcement Learning
X. Zhang, Y. Ma, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2020
Policy Teaching via Environment Poisoning: Training-time Adversarial Attacks against Reinforcement Learning
A. Rakhsha, G. Radanovic, R. Devidze, X. Zhu, A. Singla
In Proceedings of International Conference on Machine Learning (ICML), 2020
Adaptive Reward-Poisoning Attacks against Reinforcement Learning
X. Zhang, Y. Ma, A. Singla, X. Zhu
In Proceedings of International Conference on Machine Learning (ICML), 2020
Zero-shot Learning of Hint Policy via Reinforcement Learning and Program Synthesis
A. Efremov, A. Ghosh, A. Singla
In Proceedings of International Conference on Educational Data Mining (EDM), 2020
Understanding the Power and Limitations of Teaching with Imperfect Knowledge
R. Devidze*, F. Mansouri*, L. Haug, Y. Chen, A. Singla
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2020
Towards Deployment of Robust Cooperative AI Agents: An Algorithmic Framework for Learning Adaptive Policies
A. Ghosh, S. Tschiatschek, H. Mahdavi, A. Singla
In Proceedings of International Conference on Autonomous Agents & Multiagent Systems (AAMAS), 2020
Can A User Guess What Her Followers Want?
A. De, A. Singla, U. Upadhyay, M. Gomez-Rodriguez
In Proceedings of International Conference on Web Search and Data Mining (WSDM), 2020
Environment Shaping in Reinforcement Learning using State Abstraction
P. Kamalaruban, R. Devidze, V. Cevher, A. Singla
Workshop on Challenges of Real World Reinforcement Learning at NeurIPS, 2020
Preference-Based Batch and Sequential Teaching
F. Mansouri, Y. Chen, A. Vartanian, X. Zhu, A. Singla
arXiv 2010.10012, 2020 (longer version of the NeurIPS'19 paper)

2019

Preference-Based Batch and Sequential Teaching: Towards a Unified View of Models
F. Mansouri, Y. Chen, A. Vartanian, X. Zhu, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2019
Learner-aware Teaching: Inverse Reinforcement Learning with Preferences and Constraints
S. Tschiatschek*, A. Ghosh*, L. Haug*, R. Devidze, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2019
Teaching Multiple Concepts to a Forgetful Learner
A. Hunziker, Y. Chen, O. Mac Aodha, M. Gomez-Rodriguez, A. Krause, P. Perona, Y. Yue, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2019
Learning to Collaborate in Markov Decision Processes
G. Radanovic, R. Devidze, D. Parkes, A. Singla
In Proceedings of International Conference on Machine Learning (ICML), 2019
Efficient Learning of Smooth Probability Functions from Bernoulli Tests with Guarantees
P. Rolland, A. Kavis, A. Immer, A. Singla, V. Cevher
In Proceedings of International Conference on Machine Learning (ICML), 2019
Iterative Classroom Teaching
T. Yeo, P. Kamalaruban, A. Singla, A. Merchant, L. Faucon, T. Asselborn, P. Dillenbourg, V. Cevher
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2019
Interactive Teaching Algorithms for Inverse Reinforcement Learning
P. Kamalaruban*, R. Devidze*, V. Cevher, A. Singla
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2019
Loss-Aversively Fair Classification
J. Ali, M. B. Zafar, A. Singla, K. P. Gummadi
In Proceedings of Conference on Artificial Intelligence, Ethics, and Society (AIES), 2019
Unifying Ensemble Methods for Q-learning via Social Choice Theory
R. Chourasia, A. Singla
Workshop on Learning with Rich Experience (LIRE) at NeurIPS, 2019

2018

An Overview of Machine Teaching
X. Zhu, A. Singla, S. Zilles, A. N. Rafferty
Survey article; addition resources at https://teaching-machines.cc/
Teaching Inverse Reinforcement Learners via Features and Demonstrations
L. Haug, S. Tschiatschek, A. Singla
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2018
Understanding the Role of Adaptivity in Machine Teaching: The Case of Version Space Learners
Y. Chen, A. Singla, O. Mac Aodha, P. Perona, Y. Yue
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2018
Enhancing the Accuracy and Fairness of Human Decision Making
I. Valera, A. Singla, M. Gomez-Rodriguez
In Proceedings of Conference on Neural Information Processing Systems (NeurIPS), 2018
Data-Driven Approach Towards a Personalized Curriculum
M. Backenköhler, F. Scherzinger, A. Singla, V. Wolf
In Proceedings of International Conference on Educational Data Mining (EDM), 2018
Learning to Interact with Learning Agents
A. Singla, H. Hassani, A. Krause
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2018
Information Gathering with Peers: Submodular Optimization with Peer-Prediction Constraints
G. Radanovic, A. Singla, A. Krause, B. Faltings
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2018
Learning User Preferences to Incentivize Exploration in the Sharing Economy
C. Hirnschall, A. Singla, S. Tschiatschek, A. Krause
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2018
A Unified Approach to Quantifying Algorithmic Unfairness: Measuring Individual and Group Unfairness via Inequality Indices
T. Speicher, H. Heidari, N. Grgic-Hlaca, K. Gummadi, A. Singla, A. Weller, M. Zafar
In Proceedings of International Conference on Knowledge Discovery and Data Mining (KDD), 2018
Fake News Detection in Social Networks via Crowd Signals
S. Tschiatschek, A. Singla, M. Gomez-Rodriguez, A. Merchant, A. Krause
In Proceedings of WWW - Alternate Track on Journalism, Misinformation, and Fact-checking, 2018
Assisted Inverse Reinforcement Learning
P. Kamalaruban*, R. Devidze*, T. Yeo, T. Mittal, V. Cevher, A. Singla
Workshop on Learning by Instruction at NeurIPS, 2018

2017

Learning and Incentives in Crowd-Powered Systems
A. Singla
PhD thesis, ETH Zurich, 2017
Selecting Sequences of Items via Submodular Maximization
S. Tschiatschek, A. Singla, A. Krause
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2017

2016

Actively Learning Hemimetrics with Applications to Eliciting User Preferences
A. Singla, S. Tschiatschek, A. Krause
In Proceedings of International Conference on Machine Learning (ICML), 2016
Noisy Submodular Maximization via Adaptive Sampling with Applications to Crowdsourced Image Collection Summarization
A. Singla, S. Tschiatschek, A. Krause
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2016
Learning and Feature Selection under Budget Constraints in Crowdsourcing
B. Nushi, A. Singla, A. Krause, D. Kossmann
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2016
Evaluating Task-Dependent Taxonomies for Navigation
Y. Sun, A. Singla, T. Yan, A. Krause, D. Fox
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2016

2015

Incentivizing Users for Balancing Bike Sharing Systems
A. Singla, M. Santoni, G. Bartok, P. Mukerji, M. Meenen, A. Krause
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2015
Information Gathering in Networks via Active Exploration
A. Singla, E. Horvitz, P. Kohli, R. White, A. Krause
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2015
Building Hierarchies of Concepts via Crowdsourcing
Y. Sun, A. Singla, D. Fox, A. Krause
In Proceedings of International Joint Conference on Artificial Intelligence (IJCAI), 2015
Crowd Access Path Optimization: Diversity Matters
B. Nushi, A. Singla, A. Gruenheid, E. Zamanian, A. Krause, D. Kossmann
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2015
Learning to Hire Teams
A. Singla, E. Horvitz, P. Kohli, A. Krause
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), short paper, 2015

2014

Near-Optimally Teaching the Crowd to Classify
A. Singla, I. Bogunovic, G. Bartok, A. Karbasi, A. Krause
In Proceedings of International Conference on Machine Learning (ICML), 2014
Stochastic Privacy
A. Singla, E. Horvitz, E. Kamar, R. W. White
In Proceedings of AAAI Conference on Artificial Intelligence (AAAI), 2014
Mechanism Design for Crowdsourcing Markets with Heterogeneous Tasks
G. Goel, A. Nikzad, A. Singla
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2014
From Devices to People: Attribution of Search Activity in Multi-User Settings
R. W. White, A. Hassan, A. Singla, E. Horvitz
In Proceedings of International World Wide Web Conference (WWW), 2014
Quantifying Web-Search Privacy
A. Gervais, R. Shokri, A. Singla, S. Capkun, V. Lenders
In Proceedings of ACM Conference on Computer and Communications Security (CCS), 2014
Allocating Tasks to Workers with Matching Constraints: Truthful Mechanisms for Crowdsourcing Markets
G. Goel, A. Nikzad, A. Singla
In Proceedings of International World Wide Web Conference (WWW), short paper, 2014
Enhancing Personalization via Search Activity Attribution
A. Singla, R. W. White, A. Hassan, E. Horvitz
In Proceedings of International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR), short paper, 2014
Contextual Procurement in Online Crowdsourcing Markets
A. Singla, I. Lienert, G. Bartok, A. Krause
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), short paper, 2014

2013

Incentives for Privacy Tradeoff in Community Sensing
A. Singla, A. Krause
In Proceedings of AAAI Conference on Human Computation and Crowdsourcing (HCOMP), 2013
Truthful Incentives in Crowdsourcing Tasks using Regret Minimization Mechanisms
A. Singla, A. Krause
In Proceedings of International World Wide Web Conference (WWW), 2013
On Actively Teaching the Crowd to Classify
A. Singla, I. Bogunovic, G. Bartok, A. Karbasi, A. Krause
Workshop on Data Driven Education at NeurIPS, 2013

Imprint / Data Protection