Asking the Right Questions: Learning Interpretable Action Models Through Query Answering
Authors: Pulkit Verma, Shashank Rao Marpally, Siddharth Srivastava12024-12033
AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Empirical evaluation of our approach shows that despite the intractable search space of possible agent models, our approach allows correct and scalable estimation of interpretable agent models for a wide class of black-box autonomous agents. Our results also show that this approach can use predicate classifiers to learn interpretable models of planning agents that represent states as images. |
| Researcher Affiliation | Academia | Pulkit Verma, Shashank Rao Marpally, and Siddharth Srivastava School of Computing, Informatics, and Decision Systems Engineering Arizona State University, Tempe, AZ 85281, USA {verma.pulkit, smarpall, siddharths}@asu.edu |
| Pseudocode | Yes | Algorithm 1 Agent Interrogation Algorithm (AIA) and Algorithm 2 Query Generation Algorithm are presented with structured steps. |
| Open Source Code | Yes | Code available at https://git.io/Jtpej |
| Open Datasets | Yes | We tested AIA on two types of agents: symbolic agents that use models from the IPC (unknown to AIA), and simulator agents that report states as images using PDDLGym. |
| Dataset Splits | No | The paper states that "10 different problem instances were used to obtain average performance estimates" and "We used a maximum of 60 such random initial states for each domain". However, it does not specify explicit training/validation/test dataset splits with percentages, sample counts, or references to predefined splits for reproducibility. |
| Hardware Specification | Yes | All experiments were executed on 5.0 GHz Intel i9-9900 CPUs with 64 GB RAM running Ubuntu 18.04. |
| Software Dependencies | No | The paper mentions software like Python, Fast Downward, FF, Madagascar, and PDDLGym but does not provide specific version numbers for any of them (e.g., "We implemented AIA in Python", "We used Fast Downward", "we also tried using FF", "We used Madagascar", "PDDLGym framework"). |
| Experiment Setup | Yes | In this implementation, initial states (S, line 1 in Algorithm 1) were collected by making the agent perform random walks in a simulated environment. We used a maximum of 60 such random initial states for each domain in our experiments. |