mlsanityData to 14 Oct 2026

Understanding the Power and Limitations of Teaching with Imperfect Knowledge

arXiv 2003.09712 ↗First posted 21 Mar 2020cs.LG cs.AI stat.MLcited by 23

Not on the map. Why?

Abstract (arXiv)

Machine teaching studies the interaction between a teacher and a student/learner where the teacher selects training examples for the learner to learn a specific task. The typical assumption is that the teacher has perfect knowledge of the task---this knowledge comprises knowing the desired learning target, having the exact task representation used by the learner, and knowing the parameters capturing the learning dynamics of the learner. Inspired by real-world applications of machine teaching in education, we consider the setting where teacher's knowledge is limited and noisy, and the key research question we study is the following: When does a teacher succeed or fail in effectively teaching a learner using its imperfect knowledge? We answer this question by showing connections to how imperfect knowledge affects the teacher's solution of the corresponding machine teaching problem when constructing optimal teaching sets. Our results have important implications for designing robust teaching algorithms for real-world applications.

Key facts. Cited by 23 papers in the map (data through 14 Oct 2026). First posted on arXiv 21 Mar 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 7; 2023: 6; 2024: 1; 2025: 0; 2026: 1.

23 papers.

Sort:

By area:

  1. 2022Learning Neuro-Symbolic Skills for Bilevel Planningcited by 58
  2. 2021Learning Neuro-Symbolic Relational Transition Models for Bilevel Planningcited by 43
  3. 2021Heuristic-Guided Reinforcement Learningcited by 42
  4. 2023World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challengescited by 36
  5. 2023Learning adaptive planning representations with natural language guidancecited by 36
  6. 2021Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environmentscited by 26
  7. 2021Classical Planning in Deep Latent Spacecited by 22
  8. 2022Learning Efficient Abstract Planning Models that Choose What to Predictcited by 17
  9. 2021Safe Learning of Lifted Action Modelscited by 16
  10. 2022Goal Recognition as Reinforcement Learningcited by 9
  11. 2023PDSketch: Integrated Planning Domain Programming and Learningcited by 7
  12. 2021Planning from Pixels in Environments with Combinatorially Hard Search Spacescited by 5
11 more
  1. 2021Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agentscited by 4
  2. 2023Discovering Predictive Relational Object Symbols with Symbolic Attentive Layerscited by 3
  3. 2022Learning First-Order Symbolic Planning Representations That Are Groundedcited by 2
  4. 2021Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Ataricited by 1
  5. 2022Learning Visual Planning Models from Partially Observed Imagescited by 1
  6. 2023Current and Future Challenges in Knowledge Representation and Reasoningcited by 1
  7. 2024Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networkscited by 1
  8. 2026Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learningcited by 1
  9. 2022Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RLcited by 0
  10. 2022Dr. Neurosymbolic, or: How I Learned to Stop Worrying and Accept Statisticscited by 0
  11. 2023Synthesis of Procedural Models for Deterministic Transition Systemscited by 0