Competing for Resources: Estimating Adversary Strategy for Effective Plan Generation

Authors: Lukáš Chrpa, Pavel Rytíř, Rostislav Horčík, Stefan Edelkamp9707-9715

AAAI 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We empirically evaluate our approach leveraging sampling of competitor s actions by comparing it to the naive approach optimising the make-span (not taking the competing agent into account at all) and to Nash Equilibrium (mixed) strategies.
Researcher Affiliation Academia Faculty of Electrical Engineering, Czech Technical University in Prague {lukas.chrpa, pavel.rytir, rostislav.horcik, stefan.edelkamp}@fel.cvut.cz
Pseudocode Yes Algorithm 1: Estimating earliest action application and fact occurrence time; Algorithm 2: Estimating adversary strategy
Open Source Code Yes Code and benchmarks can be found at https://gitlab.com/FRASProject/aaai22-competing-for-resources
Open Datasets No The paper mentions using "Resource Hunting domain" and "Taxi domain" as case studies for experiments but does not provide specific access information (link, DOI, citation with authors/year) for these datasets to be publicly available.
Dataset Splits No The paper does not provide specific dataset split information (exact percentages, sample counts, citations to predefined splits, or detailed splitting methodology) for training, validation, or testing.
Hardware Specification Yes We ran the experiments on Linux with 2.10GHz Intel Xeon CPU E5-2620 v4 with 32GB RAM.
Software Dependencies No The paper mentions software like "PDDL 2.1", "Temporal Fast Downward (Eyerich, Mattm uller, and R oger 2009)", "Fast Downward planner (Helmert 2006)", and "CPT4 (Vidal 2011)" but does not provide specific version numbers for these software dependencies or libraries.
Experiment Setup No The paper describes the general experimental setup (e.g., comparison methods, domains, planner choices) but does not provide specific hyperparameter values, training configurations, or detailed system-level settings used for the experiments.