Zero-Sum Games between Mean-Field Teams: Reachability-Based Analysis under Mean-Field Sharing

Authors: Yue Guan, Mohammad Afshari, Panagiotis Tsiotras

AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental The ϵ-optimality of the resulting strategies is established in the original finite-population game, and the theoretical guarantees are verified by numerical examples.
Researcher Affiliation Academia Yue Guan, Mohammad Afshari, Panagiotis Tsiotras Georgia Institute of Technology {yguan44, mafshari, tsiotras}@gatech.edu
Pseudocode No The paper describes a dynamic programming recursion scheme with mathematical equations (8, 9, 10, 11) but does not provide a formal pseudocode block or algorithm.
Open Source Code No The paper does not provide any link or explicit statement about the availability of its source code.
Open Datasets No The paper uses numerical examples based on a specific problem setup ('a simple team game on a two-node graph', 'a ZS-MFTG with T =2') rather than a publicly available dataset with concrete access information.
Dataset Splits No The paper does not specify any training/test/validation dataset splits. It relies on numerical examples with a described problem setup.
Hardware Specification No The paper does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running its numerical examples.
Software Dependencies No The paper does not mention any specific software or library names with version numbers that would be needed to replicate the experiments.
Experiment Setup Yes For both examples, the state spaces are X = {x1, x2} and Y = {y1, y2}, and the action spaces are U = {u1, u2} and V = {v1, v2}. The coordinator game values in Figure 3 are computed through discretization, where the two-dimensional simplexes P(X) and P(Y) are meshed into 1,000 bins.