A Unified Framework for Planning in Adversarial and Cooperative Environments

Authors: Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati2479-2487

AAAI 2019 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also present an empirical evaluation to show the feasibility and usefulness of our approaches using IPC domains. 5 Empirical Evaluation We now present an empirical analysis of all four approaches.
Researcher Affiliation Academia Anagha Kulkarni, Siddharth Srivastava, Subbarao Kambhampati School of Computing, Informatics, and Decision Systems Engineering Arizona State University, Tempe, AZ 85281 USA {anaghak, siddharths, rao} @ asu.edu
Pseudocode Yes Algorithm 1: Plan Computation
Open Source Code No We modified the STRIPS planner Pyperplan (Alkhazraji et al. 2016) to implement our algorithms. We used the hsa (Keyder and Geffner 2008) heuristic of Pyperplan because it gave the best results in terms of computation time. The paper does not state that their own code is open-source.
Open Datasets Yes We use three IPC domains, namely Blocksworld, Logistics and Driverlog to evaluate our approach.
Dataset Splits No No specific dataset split information (percentages, counts, or explicit standard splits for training/validation/testing) is provided.
Hardware Specification Yes We ran our experiments on 12 core Intel Xeon CPU with an E5-2643 v3@3.40GHz processor with a 64G RAM with 20 minutes time-out.
Software Dependencies No The paper mentions 'Pyperplan (Alkhazraji et al. 2016)' and 'hsa (Keyder and Geffner 2008) heuristic' but does not specify their version numbers or any other software dependencies with versions.
Experiment Setup Yes We ran the experiments with k = 3, j = 2, ℓ= 3, m = 3, dmin = 0.25 and dmax = 0.50 for all the domains.