Limited Lookahead in Imperfect-Information Games

Authors: Christian Kroer, Tuomas Sandholm

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

Reproducibility Variable Result LLM Response
Research Type Experimental The impact of limited lookahead is then investigated experimentally. (Abstract) In this section we experimentally investigate how much utility can be gained by optimally exploiting a limited-lookahead player. (Section 6)
Researcher Affiliation Academia Christian Kroer and Tuomas Sandholm Computer Science Department Carnegie Mellon University ckroer@cs.cmu.edu, sandholm@cs.cmu.edu
Pseudocode No The paper describes mathematical formulations and algorithms in text and equations (e.g., MIP (12)), but does not provide a clearly labeled pseudocode block or algorithm.
Open Source Code No No explicit statement or link providing concrete access to source code for the methodology described in this paper.
Open Datasets Yes We conduct experiments on Kuhn poker [Kuhn, 1950], a canonical testbed for game-theoretic algorithms, and a larger simplified poker game that we call KJ.
Dataset Splits No The paper refers to game environments (Kuhn poker, KJ) as testbeds but does not specify data splits (e.g., train/validation/test percentages or counts) typically associated with machine learning datasets.
Hardware Specification No No specific hardware details (e.g., GPU/CPU models, memory) used for running experiments are provided.
Software Dependencies No No specific software dependencies with version numbers (e.g., Python, PyTorch, CPLEX) are mentioned.
Experiment Setup No The paper describes the node evaluation heuristic and noise models, but does not provide specific experimental setup details such as hyperparameters (e.g., learning rate, batch size) or training configurations.