The Minds of Many: Opponent Modeling in a Stochastic Game

Authors: Friedrich Burkhard von der Osten, Michael Kirley, Tim Miller

IJCAI 2017 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Simulation results demonstrate that the model performs well under uncertainty and that stereotyping allows larger groups of agents to be modelled robustly.
Researcher Affiliation Academia School of Computing and Information Systems The University of Melbourne, Australia fvon@student.unimelb.edu.au, {m.kirley,tmiller}@unimelb.edu.au
Pseudocode No The paper describes the model and its components using mathematical equations and textual descriptions, but it does not contain structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide concrete access to source code for the methodology described, nor does it explicitly state that the code is publicly available.
Open Datasets No The paper conducts simulations using a defined game model (CPRG) rather than relying on a pre-existing, externally available dataset. While the game dynamics are described and referenced, no concrete access information to a downloadable dataset used for the experiments is provided.
Dataset Splits No The paper conducts simulations and describes the number of rounds and repetitions for each setting, but it does not specify explicit training/validation/test dataset splits as it generates its own data through simulation.
Hardware Specification No The paper does not provide specific hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers, needed to replicate the experiment.
Experiment Setup Yes Table 1 shows the parameters and variables used in the experiments: λ Learning parameter 0.5, t Timescale for assessing agents 10, Xmin Minimum effort 100, Xmax Maximum effort 500, A # of actions available to agents 10, S # of game states agents recognize 5, n # of agents in the game [2,10], C # of categories for segmentation [1,4], h % of RND agents in the population [20,50]. Each simulation is run for 5000 rounds, with each setting repeated 50 times.