Contrastive Explanations of Plans Through Model Restrictions
- URL: http://arxiv.org/abs/2103.15575v1
- Date: Mon, 29 Mar 2021 12:47:15 GMT
- Title: Contrastive Explanations of Plans Through Model Restrictions
- Authors: Benjamin Krarup and Senka Krivic and Daniele Magazzeni and Derek Long
and Michael Cashmore and David E. Smith
- Abstract summary: We frame Explainable AI Planning in the context of the plan negotiation problem.
We present the results of a user study that demonstrates that when users ask questions about plans, those questions are contrastive.
We use the data from this study to construct a taxonomy of user questions that often arise during plan negotiation.
- Score: 11.259587284318833
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: In automated planning, the need for explanations arises when there is a
mismatch between a proposed plan and the user's expectation. We frame
Explainable AI Planning in the context of the plan negotiation problem, in
which a succession of hypothetical planning problems are generated and solved.
The object of the negotiation is for the user to understand and ultimately
arrive at a satisfactory plan. We present the results of a user study that
demonstrates that when users ask questions about plans, those questions are
contrastive, i.e. "why A rather than B?". We use the data from this study to
construct a taxonomy of user questions that often arise during plan
negotiation. We formally define our approach to plan negotiation through model
restriction as an iterative process. This approach generates hypothetical
problems and contrastive plans by restricting the model through constraints
implied by user questions. We formally define model-based compilations in
PDDL2.1 of each constraint derived from a user question in the taxonomy, and
empirically evaluate the compilations in terms of computational complexity. The
compilations were implemented as part of an explanation framework that employs
iterative model restriction. We demonstrate its benefits in a second user
study.
Related papers
- Planning as In-Painting: A Diffusion-Based Embodied Task Planning
Framework for Environments under Uncertainty [56.30846158280031]
Task planning for embodied AI has been one of the most challenging problems.
We propose a task-agnostic method named 'planning as in-painting'
The proposed framework achieves promising performances in various embodied AI tasks.
arXiv Detail & Related papers (2023-12-02T10:07:17Z) - PlaSma: Making Small Language Models Better Procedural Knowledge Models for (Counterfactual) Planning [77.03847056008598]
PlaSma is a novel two-pronged approach to endow small language models with procedural knowledge and (constrained) language planning capabilities.
We develop symbolic procedural knowledge distillation to enhance the commonsense knowledge in small language models and an inference-time algorithm to facilitate more structured and accurate reasoning.
arXiv Detail & Related papers (2023-05-31T00:55:40Z) - Temporal Planning with Incomplete Knowledge and Perceptual Information [0.0]
This paper presents a new planning approach that combines contingent plan construction within a temporal planning framework.
We propose a small extension to the Planning Domain Definition Language (PDDL) to model incomplete, (ii) knowledge sensing actions.
We also introduce a new set of planning domains to evaluate our solver, which has shown good performance on a variety of problems.
arXiv Detail & Related papers (2022-07-20T07:26:08Z) - Position Paper: Online Modeling for Offline Planning [2.8326418377665346]
A key part of AI planning research is the representation of action models.
Despite the maturity of the field, AI planning technology is still rarely used outside the research community.
We argue that this is because the modeling process is assumed to have taken place and completed prior to the planning process.
arXiv Detail & Related papers (2022-06-07T14:48:08Z) - On Exploiting Hitting Sets for Model Reconciliation [53.81101846598925]
In human-aware planning, a planning agent may need to provide an explanation to a human user on why its plan is optimal.
A popular approach to do this is called model reconciliation, where the agent tries to reconcile the differences in its model and the human's model.
We present a logic-based framework for model reconciliation that extends beyond the realm of planning.
arXiv Detail & Related papers (2020-12-16T21:25:53Z) - Iterative Planning with Plan-Space Explanations: A Tool and User Study [5.779503104475269]
We implement a tool for human-guided iterative planning including plan-space explanations.
The tool runs in standard Web browsers, and provides simple user interfaces for both developers and users.
We conduct a first user study, whose outcome indicates the usefulness of plan-property dependency explanations in iterative planning.
arXiv Detail & Related papers (2020-11-19T08:15:13Z) - Forethought and Hindsight in Credit Assignment [62.05690959741223]
We work to understand the gains and peculiarities of planning employed as forethought via forward models or as hindsight operating with backward models.
We investigate the best use of models in planning, primarily focusing on the selection of states in which predictions should be (re)-evaluated.
arXiv Detail & Related papers (2020-10-26T16:00:47Z) - A Revised Generative Evaluation of Visual Dialogue [80.17353102854405]
We propose a revised evaluation scheme for the VisDial dataset.
We measure consensus between answers generated by the model and a set of relevant answers.
We release these sets and code for the revised evaluation scheme as DenseVisDial.
arXiv Detail & Related papers (2020-04-20T13:26:45Z) - STRIPS Action Discovery [67.73368413278631]
Recent approaches have shown the success of classical planning at synthesizing action models even when all intermediate states are missing.
We propose a new algorithm to unsupervisedly synthesize STRIPS action models with a classical planner when action signatures are unknown.
arXiv Detail & Related papers (2020-01-30T17:08:39Z)
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.