Opponent-Model Search in Games with Incomplete Information
Authors: Junkang Li, Bruno Zanuttini, Véronique Ventos
AAAI 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We propose algorithms for computing optimal and/or robust strategies in games with incomplete information, given various types of knowledge about opponent models. As an application, we describe a framework for reasoning about an opponent s reasoning in such games, where opponent models arise naturally. |
| Researcher Affiliation | Collaboration | 1Nukk AI, Paris, France 2Normandie Univ.; UNICAEN, ENSICAEN, CNRS, GREYC, 14 000 Caen, France |
| Pseudocode | Yes | Algorithm 1: Generic Minimax Algorithm |
| Open Source Code | No | The paper includes a link 'A long version with proofs of all claims is available at https://hal.science/hal-04100646.' This link points to a preprint of the paper, not to source code for the methodology described. |
| Open Datasets | No | The paper provides illustrative examples (Figure 1, Figure 2) and a 'Real-Life Example' of a Bridge deal to demonstrate the theoretical framework. However, it does not use a publicly available or open dataset with access information for empirical evaluation. |
| Dataset Splits | No | The paper does not conduct empirical experiments with datasets; therefore, it does not provide details on training, validation, or test dataset splits. |
| Hardware Specification | No | The paper focuses on theoretical aspects and algorithm design. It does not report on empirical experiments, and therefore, no hardware specifications are mentioned. |
| Software Dependencies | No | The paper focuses on theoretical algorithms and a framework. It does not mention specific software dependencies with version numbers that would be required to reproduce any implementation or experiments. |
| Experiment Setup | No | The paper is theoretical and describes algorithms and a framework. It does not report on empirical experiments, and thus, no experimental setup details like hyperparameters or training configurations are provided. |