Simultaneous Abstraction and Equilibrium Finding in Games

Authors: Noam Brown, Tuomas Sandholm

IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental 7 Experiments We tested our algorithm on a game we coin continuous Leduc Hold em (CLH)... Figure 1 shows that Recovery-1.01 outperformed all the fixed abstractions at every point in the run.
Researcher Affiliation Academia Noam Brown Computer Science Department Carnegie Mellon University noamb@cs.cmu.edu Tuomas Sandholm Computer Science Department Carnegie Mellon University sandholm@cs.cmu.edu
Pseudocode No The paper describes algorithms but does not provide structured pseudocode blocks or algorithm figures.
Open Source Code No The paper does not provide any concrete access information (e.g., specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described.
Open Datasets No We tested our algorithm on a game we coin continuous Leduc Hold em (CLH)... The paper describes a game they "coin", implying it's not a standard public dataset, and provides no access details for any data used for experiments.
Dataset Splits No The paper describes the game rules for 'continuous Leduc Hold em' but does not provide specific dataset split information (percentages, sample counts, or citations to predefined splits) needed to reproduce data partitioning.
Hardware Specification No The paper does not specify any hardware details (e.g., exact GPU/CPU models, processor types, or memory amounts) used for running its experiments.
Software Dependencies No The paper mentions algorithms like CFR but does not specify any software names with version numbers (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4) needed to replicate the experiment.
Experiment Setup Yes The automated abstractions considered adding actions every 5 iterations according to the heuristic presented in Section 5 using regret transfer to estimate regret... Recovery-1.01 and Transfer both multiply the left term in the condition by 1.01.