Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Stochastic Market Games
Authors: Kyrill Schmid, Lenz Belzner, Robert Müller, Johannes Tochtermann, Claudia Linnhoff-Popien
IJCAI 2021 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We empirically find that the presence of markets can improve both the overall result and agent individual returns via their trading activities. |
| Researcher Affiliation | Academia | 1LMU Munich 2Technische Hochschule Ingolstadt |
| Pseudocode | Yes | pseudocode given in Algorithm 1 |
| Open Source Code | No | The paper does not provide any statement or link indicating that the source code for the described methodology is publicly available. |
| Open Datasets | No | The paper introduces custom domains called 'Smartfactory' and 'Refinery' for evaluation and does not provide access information or citations for publicly available datasets. |
| Dataset Splits | No | The paper describes training processes and evaluation runs but does not specify train/validation/test dataset splits, percentages, or sample counts. |
| Hardware Specification | No | The paper does not provide any specific details about the hardware used for running the experiments, such as GPU or CPU models. |
| Software Dependencies | No | The paper refers to various algorithms and models (DQN, PPO, MADDPG) but does not specify any software dependencies with version numbers. |
| Experiment Setup | Yes | For the experiment we set R1 = 0.375 and R2 = 2.625...two independent Q-learners were trained over 25 independent runs for each level of conflict α, where each run consisted of 4000 consecutive steps. ... here we used p = 1.9. ... In all runs we set rhigh = 5, rlow = 1 tinactive = 8 in the Smartfactory and rhigh = 5, rlow = 0.02 in the Refinery. ... All settings were tested with 4, 8 and 16 agents... |