Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind

• URL: http://arxiv.org/abs/2309.17275v1
• Date: Fri, 29 Sep 2023 14:27:53 GMT
• Title: Utility-based Adaptive Teaching Strategies using Bayesian Theory of Mind
• Authors: Cl\'emence Grislain, Hugo Caselles-Dupr\'e, Olivier Sigaud, Mohamed Chetouani
• Abstract summary: We build on cognitive science to design teacher agents that tailor their teaching strategies to the learners. Our ToM-equipped teachers construct models of learners' internal states from observations. Experiments in simulated environments demonstrate that learners taught this way are more efficient than those taught in a learner-agnostic way.
• Score: 7.754711372795438
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Good teachers always tailor their explanations to the learners. Cognitive scientists model this process under the rationality principle: teachers try to maximise the learner's utility while minimising teaching costs. To this end, human teachers seem to build mental models of the learner's internal state, a capacity known as Theory of Mind (ToM). Inspired by cognitive science, we build on Bayesian ToM mechanisms to design teacher agents that, like humans, tailor their teaching strategies to the learners. Our ToM-equipped teachers construct models of learners' internal states from observations and leverage them to select demonstrations that maximise the learners' rewards while minimising teaching costs. Our experiments in simulated environments demonstrate that learners taught this way are more efficient than those taught in a learner-agnostic way. This effect gets stronger when the teacher's model of the learner better aligns with the actual learner's state, either using a more accurate prior or after accumulating observations of the learner's behaviour. This work is a first step towards social machines that teach us and each other, see https://teacher-with-tom.github.io.

Related papers

• YODA: Teacher-Student Progressive Learning for Language Models [82.0172215948963]
  This paper introduces YODA, a teacher-student progressive learning framework. It emulates the teacher-student education process to improve the efficacy of model fine-tuning. Experiments show that training LLaMA2 with data from YODA improves SFT with significant performance gain.
  arXiv  Detail & Related papers  (2024-01-28T14:32:15Z)
• Can Language Models Teach Weaker Agents? Teacher Explanations Improve Students via Personalization [84.86241161706911]
  We show that teacher LLMs can indeed intervene on student reasoning to improve their performance. We also demonstrate that in multi-turn interactions, teacher explanations generalize and learn from explained data. We verify that misaligned teachers can lower student performance to random chance by intentionally misleading them.
  arXiv  Detail & Related papers  (2023-06-15T17:27:20Z)
• Reinforcement Teaching [43.80089037901853]
  We propose Reinforcement Teaching: a framework for meta-learning in which a teaching policy is learned, through reinforcement, to control a student's learning process. The student's learning process is modelled as a Markov reward process and the teacher, with its action-space, interacts with the induced Markov decision process. We show that, for many learning processes, the student's learnable parameters form a Markov state. To avoid having the teacher learn directly from parameters, we propose the Embedder that learns a representation of a student's state from its input/output behaviour.
  arXiv  Detail & Related papers  (2022-04-25T18:04:17Z)
• Iterative Teacher-Aware Learning [136.05341445369265]
  In human pedagogy, teachers and students can interact adaptively to maximize communication efficiency. We propose a gradient optimization based teacher-aware learner who can incorporate teacher's cooperative intention into the likelihood function.
  arXiv  Detail & Related papers  (2021-10-01T00:27:47Z)
• Distribution Matching for Machine Teaching [64.39292542263286]
  Machine teaching is an inverse problem of machine learning that aims at steering the student learner towards its target hypothesis. Previous studies on machine teaching focused on balancing the teaching risk and cost to find those best teaching examples. This paper presents a distribution matching-based machine teaching strategy.
  arXiv  Detail & Related papers  (2021-05-06T09:32:57Z)
• Teaching to Learn: Sequential Teaching of Agents with Inner States [20.556373950863247]
  We introduce a multi-agent formulation in which learners' inner state may change with the teaching interaction. In order to teach such learners, we propose an optimal control approach that takes the future performance of the learner after teaching into account.
  arXiv  Detail & Related papers  (2020-09-14T07:03:15Z)
• Using Machine Teaching to Investigate Human Assumptions when Teaching Reinforcement Learners [26.006964607579004]
  We focus on a common reinforcement learning method, Q-learning, and examine what assumptions people have using a behavioral experiment. We use a deep learning approximation method which simulates learners in the environment and learns to predict how feedback affects the learner's internal states. Our results reveal how people teach using evaluative feedback and provide guidance for how engineers should design machine agents in a manner that is intuitive for people.
  arXiv  Detail & Related papers  (2020-09-05T06:32:38Z)
• Interaction-limited Inverse Reinforcement Learning [50.201765937436654]
  We present two different training strategies: Curriculum Inverse Reinforcement Learning (CIRL) covering the teacher's perspective, and Self-Paced Inverse Reinforcement Learning (SPIRL) focusing on the learner's perspective. Using experiments in simulations and experiments with a real robot learning a task from a human demonstrator, we show that our training strategies can allow a faster training than a random teacher for CIRL and than a batch learner for SPIRL.
  arXiv  Detail & Related papers  (2020-07-01T12:31:52Z)
• Iterative Machine Teaching without Teachers [12.239246363539634]
  Existing studies on iterative machine teaching assume that there are teachers who know the true answers of all teaching examples. In this study, we consider an unsupervised case where such teachers do not exist. Students are given a teaching example at each iteration, but there is no guarantee if the corresponding label is correct.
  arXiv  Detail & Related papers  (2020-06-27T11:21:57Z)
• Explainable Active Learning (XAL): An Empirical Study of How Local Explanations Impact Annotator Experience [76.9910678786031]
  We propose a novel paradigm of explainable active learning (XAL), by introducing techniques from the recently surging field of explainable AI (XAI) into an Active Learning setting. Our study shows benefits of AI explanation as interfaces for machine teaching--supporting trust calibration and enabling rich forms of teaching feedback, and potential drawbacks--anchoring effect with the model judgment and cognitive workload.
  arXiv  Detail & Related papers  (2020-01-24T22:52:18Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.