Analyzing Intentional Behavior in Autonomous Agents under Uncertainty

Authors: Filip Cano Córdoba, Samuel Judson, Timos Antonopoulos, Katrine Bjørner, Nicholas Shoemaker, Scott J. Shapiro, Ruzica Piskac, Bettina Könighofer

IJCAI 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental In a case study, we show how our method can distinguish between intentional and accidental traffic collisions. ... In this section, we showcase our method on a traffic-related scenario related to Examples 1-2, and that is illustrated in Figure 2. ... All experiments were executed on an Intel Core i5 CPU with 16GB of RAM running Ubuntu 20.04. We use TEMPEST [Pranger et al., 2021] as our model checking engine. 6.1 Model of Environment 6.2 Analysis of a Trace 6.3 Comparative Analysis of Several Agents
Researcher Affiliation Academia 1Graz University of Technology 2Yale University 3 New York University {filip.cano, bettina.koenighofer}@iaik.tugraz.at, {samuel.judson, timos.antonopoulos, nick.shoemaker, scott.shapiro, ruzica.piskac}@yale.edu, kbjorner@nyu.edu
Pseudocode No The paper describes the methodology in prose and includes a high-level flowchart (Figure 1), but it does not provide structured pseudocode or algorithm blocks.
Open Source Code Yes Find code and experimental details in the accompanying repository https://github.com/filipcano/intentional-autonomous-agents.
Open Datasets No The paper describes modeling a custom environment and scenario (Section 6.1) rather than using a pre-existing, publicly available dataset with concrete access information. No dataset is mentioned for public access.
Dataset Splits No The paper analyzes a specific scenario and generates counterfactual scenarios for analysis, but it does not describe a traditional machine learning experimental setup with training, validation, and test dataset splits with specified percentages or sample counts.
Hardware Specification Yes All experiments were executed on an Intel Core i5 CPU with 16GB of RAM running Ubuntu 20.04.
Software Dependencies No The paper mentions using "TEMPEST [Pranger et al., 2021] as our model checking engine" and "Ubuntu 20.04", but it does not provide specific version numbers for software libraries, frameworks, or solvers beyond the operating system.
Experiment Setup Yes As thresholds to evaluate evidence of intention, we use δL ρ = 0.25, δU ρ = 0.75 and δσ = 0.5. ... We change the following variables: Slipperiness range... Slipperiness factor... Hesitancy factor... Visibility... The variables and the ranges considered for generating counterfactuals are summarized in Table 1.