skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: Explicable Planning as Minimizing Distance from Expected Behavior
In order to achieve effective human-AI collaboration, it is necessary for an AI agent to align its behavior with the human's expectations. When the agent generates a task plan without such considerations, it may often result in inexplicable behavior from the human's point of view. This may have serious implications for the human, from increased cognitive load to more serious concerns of safety around the physical agent. In this work, we present an approach to generate explicable behavior by minimizing the distance between the agent's plan and the plan expected by the human. To this end, we learn a mapping between plan distances (distances between expected and agent plans) and human's plan scoring scheme. The plan generation process uses this learned model as a heuristic. We demonstrate the effectiveness of our approach in a delivery robot domain.  more » « less
Award ID(s):
1844524
PAR ID:
10105324
Author(s) / Creator(s):
; ; ; ; ;
Date Published:
Journal Name:
AAMAS Conference proceedings
ISSN:
2523-5699
Page Range / eLocation ID:
2075-2077
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; ; ; (, Proceedings of the Annual Meeting of the Cognitive Science Society)
    Human-AI collaboration is an increasingly commonplace part of decision-making in real world applications. However, how humans behave when collaborating with AI is not well understood. We develop metacognitive bandits, a computational model of a human's advice-seeking behavior when working with an AI. The model describes a person's metacognitive process of deciding when to rely on their own judgment and when to solicit the advice of the AI. It also accounts for the difficulty of each trial in making the decision to solicit advice. We illustrate that the metacognitive bandit makes decisions similar to humans in a behavioral experiment. We also demonstrate that algorithm aversion, a widely reported bias, can be explained as the result of a quasi-optimal sequential decision-making process. Our model does not need to assume any prior biases towards AI to produce this behavior. 
    more » « less
  2. ; ; ; (, International Conference on Principles of Knowledge Representation and Reasoning ()
    null (Ed.)
    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming. 
    more » « less
  3. (, Proceedings of the AAAI Conference on Artificial Intelligence)
    Ensuring that AI systems do what we, as humans, actually want them to do, is one of the biggest open research challenges in AI alignment and safety. My research seeks to directly address this challenge by enabling AI systems to interact with humans to learn aligned and robust behaviors. The way in which robots and other AI systems behave is often the result of optimizing a reward function. However, manually designing good reward functions is highly challenging and error prone, even for domain experts. Consider trying to write down a reward function that describes good driving behavior or how you like your bed made in the morning. While reward functions for these tasks are difficult to manually specify, human feedback in the form of demonstrations or preferences are often much easier to obtain. However, human data is often difficult to interpret, due to ambiguity and noise. Thus, it is critical that AI systems take into account epistemic uncertainty over the human's true intent. My talk will give an overview of my lab's progress along the following fundamental research areas: (1) efficiently maintaining uncertainty over human intent, (2) directly optimizing behavior to be robust to uncertainty over human intent, and (3) actively querying for additional human input to reduce uncertainty over human intent. 
    more » « less
  4. ; ; ; (, Proceedings of the International Conference on Principles of Knowledge Representation and Reasoning)
    null (Ed.)
    In human-aware planning problems, the planning agent may need to explain its plan to a human user, especially when the plan appears infeasible or suboptimal for the user. A popular approach to do so is called model reconciliation, where the planning agent tries to reconcile the differences between its model and the model of the user such that its plan is also feasible and optimal to the user. This problem can be viewed as an optimization problem, where the goal is to find a subset-minimal explanation that one can use to modify the model of the user such that the plan of the agent is also feasible and optimal to the user. This paper presents an algorithm for solving such problems using answer set programming. 
    more » « less
  5. ; (, Proceedings of the AAAI Conference on Artificial Intelligence)
    Reward learning as a method for inferring human intent and preferences has been studied extensively. Prior approaches make an implicit assumption that the human maintains a correct belief about the robot's domain dynamics. However, this may not always hold since the human's belief may be biased, which can ultimately lead to a misguided estimation of the human's intent and preferences, which is often derived from human feedback on the robot's behaviors. In this paper, we remove this restrictive assumption by considering that the human may have an inaccurate understanding of the robot. We propose a method called Generalized Reward Learning with biased beliefs about domain dynamics (GeReL) to infer both the reward function and human's belief about the robot in a Bayesian setting based on human ratings. Due to the complex forms of the posteriors, we formulate it as a variational inference problem to infer the posteriors of the parameters that govern the reward function and human's belief about the robot simultaneously. We evaluate our method in a simulated domain and with a user study where the user has a bias based on the robot's appearances. The results show that our method can recover the true human preferences while subject to such biased beliefs, in contrast to prior approaches that could have misinterpreted them completely. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email