# Understanding the Power and Limitations of Teaching with Imperfect Knowledge

arXiv: https://arxiv.org/abs/2003.09712 · HTML: https://mlsanity.com/paper/2003.09712/

## Key facts

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

## Built on by (most cited first, 23 of 23)

- [Learning Neuro-Symbolic Skills for Bilevel Planning](https://mlsanity.com/paper/2206.10680/) (2022)
- [Learning Neuro-Symbolic Relational Transition Models for Bilevel Planning](https://mlsanity.com/paper/2105.14074/) (2021)
- [Heuristic-Guided Reinforcement Learning](https://mlsanity.com/paper/2106.02757/) (2021)
- [World Models and Predictive Coding for Cognitive and Developmental Robotics: Frontiers and Challenges](https://mlsanity.com/paper/2301.05832/) (2023)
- [Learning adaptive planning representations with natural language guidance](https://mlsanity.com/paper/2312.08566/) (2023)
- [Reward Poisoning in Reinforcement Learning: Attacks Against Unknown Learners in Unknown Environments](https://mlsanity.com/paper/2102.08492/) (2021)
- [Classical Planning in Deep Latent Space](https://mlsanity.com/paper/2107.00110/) (2021)
- [Learning Efficient Abstract Planning Models that Choose What to Predict](https://mlsanity.com/paper/2208.07737/) (2022)
- [Safe Learning of Lifted Action Models](https://mlsanity.com/paper/2107.04169/) (2021)
- [Goal Recognition as Reinforcement Learning](https://mlsanity.com/paper/2202.06356/) (2022)
- [PDSketch: Integrated Planning Domain Programming and Learning](https://mlsanity.com/paper/2303.05501/) (2023)
- [Planning from Pixels in Environments with Combinatorially Hard Search Spaces](https://mlsanity.com/paper/2110.06149/) (2021)
- [Eye of the Beholder: Improved Relation Generalization for Text-based Reinforcement Learning Agents](https://mlsanity.com/paper/2106.05387/) (2021)
- [Discovering Predictive Relational Object Symbols with Symbolic Attentive Layers](https://mlsanity.com/paper/2309.00889/) (2023)
- [Learning First-Order Symbolic Planning Representations That Are Grounded](https://mlsanity.com/paper/2204.11902/) (2022)
- [Is Policy Learning Overrated?: Width-Based Planning and Active Learning for Atari](https://mlsanity.com/paper/2109.15310/) (2021)
- [Learning Visual Planning Models from Partially Observed Images](https://mlsanity.com/paper/2211.15666/) (2022)
- [Current and Future Challenges in Knowledge Representation and Reasoning](https://mlsanity.com/paper/2308.04161/) (2023)
- [Three Pathways to Neurosymbolic Reinforcement Learning with Interpretable Model and Policy Networks](https://mlsanity.com/paper/2402.05307/) (2024)
- [Multi-Modal, Multi-Environment Machine Teaching for Robust Reward Learning](https://mlsanity.com/paper/2607.08647/) (2026)
- [Beyond Value: CHECKLIST for Testing Inferences in Planning-Based RL](https://mlsanity.com/paper/2206.02039/) (2022)
- [Dr. Neurosymbolic, or: How I Learned to Stop Worrying and Accept Statistics](https://mlsanity.com/paper/2209.04049/) (2022)
- [Synthesis of Procedural Models for Deterministic Transition Systems](https://mlsanity.com/paper/2307.14368/) (2023)

## 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.