Teaching Humans When To Defer to a Classifier via Examplars
- URL: http://arxiv.org/abs/2111.11297v1
- Date: Mon, 22 Nov 2021 15:52:15 GMT
- Title: Teaching Humans When To Defer to a Classifier via Examplars
- Authors: Hussein Mozannar, Arvind Satyanarayan, David Sontag
- Abstract summary: We aim to ensure that human decision makers learn a valid mental model of the agent's strengths and weaknesses.
We propose an exemplar-based teaching strategy where humans solve the task with the help of the agent.
We present a novel parameterization of the human's mental model of the AI that applies a nearest neighbor rule in local regions.
- Score: 9.851033166756274
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: Expert decision makers are starting to rely on data-driven automated agents
to assist them with various tasks. For this collaboration to perform properly,
the human decision maker must have a mental model of when and when not to rely
on the agent. In this work, we aim to ensure that human decision makers learn a
valid mental model of the agent's strengths and weaknesses. To accomplish this
goal, we propose an exemplar-based teaching strategy where humans solve the
task with the help of the agent and try to formulate a set of guidelines of
when and when not to defer. We present a novel parameterization of the human's
mental model of the AI that applies a nearest neighbor rule in local regions
surrounding the teaching examples. Using this model, we derive a near-optimal
strategy for selecting a representative teaching set. We validate the benefits
of our teaching strategy on a multi-hop question answering task using crowd
workers and find that when workers draw the right lessons from the teaching
stage, their task performance improves, we furthermore validate our method on a
set of synthetic experiments.
Related papers
- Learning to Assist Humans without Inferring Rewards [65.28156318196397]
We build upon prior work that studies assistance through the lens of empowerment.
An assistive agent aims to maximize the influence of the human's actions.
We prove that these representations estimate a similar notion of empowerment to that studied by prior work.
arXiv Detail & Related papers (2024-11-04T21:31:04Z) - Transfer Reinforcement Learning in Heterogeneous Action Spaces using Subgoal Mapping [9.81076530822611]
We propose a method that learns a subgoal mapping between the expert agent policy and the learner agent policy.
We learn this subgoal mapping by training a Long Short Term Memory (LSTM) network for a distribution of tasks.
We demonstrate that the proposed learning scheme can effectively find the subgoal mapping underlying the given distribution of tasks.
arXiv Detail & Related papers (2024-10-18T14:08:41Z) - LiFT: Unsupervised Reinforcement Learning with Foundation Models as
Teachers [59.69716962256727]
We propose a framework that guides a reinforcement learning agent to acquire semantically meaningful behavior without human feedback.
In our framework, the agent receives task instructions grounded in a training environment from large language models.
We demonstrate that our method can learn semantically meaningful skills in a challenging open-ended MineDojo environment.
arXiv Detail & Related papers (2023-12-14T14:07:41Z) - Can Foundation Models Watch, Talk and Guide You Step by Step to Make a
Cake? [62.59699229202307]
Despite advances in AI, it remains a significant challenge to develop interactive task guidance systems.
We created a new multimodal benchmark dataset, Watch, Talk and Guide (WTaG) based on natural interaction between a human user and a human instructor.
We leveraged several foundation models to study to what extent these models can be quickly adapted to perceptually enabled task guidance.
arXiv Detail & Related papers (2023-11-01T15:13:49Z) - Designing Closed-Loop Models for Task Allocation [36.04165658325371]
We exploit weak prior information on human-task similarity to bootstrap model training.
We show that the use of such a weak prior can improve task allocation accuracy, even when human decision-makers are fallible and biased.
arXiv Detail & Related papers (2023-05-31T13:57:56Z) - Inverse Online Learning: Understanding Non-Stationary and Reactionary
Policies [79.60322329952453]
We show how to develop interpretable representations of how agents make decisions.
By understanding the decision-making processes underlying a set of observed trajectories, we cast the policy inference problem as the inverse to this online learning problem.
We introduce a practical algorithm for retrospectively estimating such perceived effects, alongside the process through which agents update them.
Through application to the analysis of UNOS organ donation acceptance decisions, we demonstrate that our approach can bring valuable insights into the factors that govern decision processes and how they change over time.
arXiv Detail & Related papers (2022-03-14T17:40:42Z) - Unsupervised Domain Adaptive Person Re-Identification via Human Learning
Imitation [67.52229938775294]
In past years, researchers propose to utilize the teacher-student framework in their methods to decrease the domain gap between different person re-identification datasets.
Inspired by recent teacher-student framework based methods, we propose to conduct further exploration to imitate the human learning process from different aspects.
arXiv Detail & Related papers (2021-11-28T01:14:29Z) - AvE: Assistance via Empowerment [77.08882807208461]
We propose a new paradigm for assistance by instead increasing the human's ability to control their environment.
This task-agnostic objective preserves the person's autonomy and ability to achieve any eventual state.
arXiv Detail & Related papers (2020-06-26T04:40:11Z) - Should artificial agents ask for help in human-robot collaborative
problem-solving? [0.7251305766151019]
We propose to start from hypotheses derived from an empirical study in a human-robot interaction.
We check whether receiving help from an expert when solving a simple close-ended task allows to accelerate or not the learning of this task.
Our experiences have allowed us to conclude that, whether requested or not, a Q-learning algorithm benefits in the same way from expert help as children do.
arXiv Detail & Related papers (2020-05-25T09:15:30Z) - Human AI interaction loop training: New approach for interactive
reinforcement learning [0.0]
Reinforcement Learning (RL) in various decision-making tasks of machine learning provides effective results with an agent learning from a stand-alone reward function.
RL presents unique challenges with large amounts of environment states and action spaces, as well as in the determination of rewards.
Imitation Learning (IL) offers a promising solution for those challenges using a teacher.
arXiv Detail & Related papers (2020-03-09T15:27:48Z)
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.