Exploiting Opponents Under Utility Constraints in Sequential Games

Authors: Martino Bernasconi-de-Luca, Federico Cacciamani, Simone Fioravanti, Nicola Gatti, Alberto Marchesi, Francesco Trovò

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

Reproducibility Variable Result LLM Response
Research Type Experimental Finally, we empirically evaluate the convergence of our algorithm on standard testbeds of sequential games.
Researcher Affiliation Academia Martino Bernasconi-de-Luca Politecnico di Milano Federico Cacciamani Politecnico di Milano Simone Fioravanti Gran Sasso Science Institute Nicola Gatti Politecnico di Milano Alberto Marchesi Politecnico di Milano Francesco Trovò Politecnico di Milano
Pseudocode Yes Algorithm 1 COX-UCB Algorithm 2 Strategy selection of COX-UCB Algorithm 3 Strategy selection of ψ-COX-UCB
Open Source Code No The paper does not contain any explicit statement about making the source code available, nor does it provide a link to a code repository.
Open Datasets No The paper mentions using "standard testbed of Kuhn and Leduc poker games [Kuhn, 2016]" but does not provide a direct link, DOI, or a formal citation with author names and year in brackets/parentheses for accessing the dataset itself. The citation points to a book chapter, not a dataset source.
Dataset Splits No The paper mentions evaluating against "10 different randomly generated strategies" and executing "5 different algorithm runs," but it does not specify any training, validation, or test dataset splits in terms of percentages or sample counts from a predefined dataset. The data is generated through online game play rather than being split from a static dataset.
Hardware Specification No The paper does not provide any specific details about the hardware used for running the experiments, such as GPU/CPU models, memory, or cloud instance types.
Software Dependencies Yes We use Gurobi for solving bilinear optimization problems [Gurobi Optimization, 2021].
Experiment Setup Yes The values (α, β) needed for the utility constraints are set to α = 0.3 and β = 0.3 in all the experiments.