Exploration-Exploitation in Multi-Agent Learning: Catastrophe Theory Meets Game Theory

Authors: Stefanos Leonardos, Georgios Piliouras11263-11271

AAAI 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The above findings are visualized in systematic experiments in both low and large dimensional games along two representative exploration-exploitation policies, explore-thenexploit and cyclical learning rates (Experiments Section).
Researcher Affiliation Academia Stefanos Leonardos, Georgios Piliouras Singapore University of Technology and Design, 8 Somapah Road, 487372 Singapore, {stefanos leonardos ; georgios}@sutd.edu.sg
Pseudocode No The paper provides mathematical equations and derivations, but no structured pseudocode or algorithm blocks were found.
Open Source Code No No explicit statement or link regarding the availability of open-source code for the described methodology was found.
Open Datasets No The experiments are conducted on coordination games and randomly generated potential games, but no specific publicly available or open dataset with access information (link, DOI, or formal citation) is provided.
Dataset Splits No The paper describes experimental scenarios but does not provide specific details on training, validation, or test dataset splits (e.g., percentages or sample counts).
Hardware Specification No The paper does not provide specific details about the hardware (e.g., GPU/CPU models, memory) used for running the experiments.
Software Dependencies No The paper does not provide specific software dependencies or version numbers (e.g., programming languages, libraries, solvers) used for implementation.
Experiment Setup No The paper describes the general policies (ETE, CLR-1) and their behavior, but lacks specific numerical hyperparameters, training configurations, or system-level settings for the experiments.