Solving Heads-Up Limit Texas Hold'em
Authors: Oskari Tammelin, Neil Burch, Michael Johanson, Michael Bowling
IJCAI 2015 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | In this section, our experiments will demonstrate the empirical advantages of CFR+ over CFR, and highlight the engineering decisions that must be made for large-scale implementations. Our domain for these experiments is Rhode Island hold em, a small synthetic poker game with a similar structure to HULHE. We also demonstrate the strong performance of CFR+ is not limited to poker-like games by comparing CFR and CFR+ in matrix games. |
| Researcher Affiliation | Collaboration | Oskari Tammelin,1 Neil Burch,2 Michael Johanson2 and Michael Bowling2 1http://jeskola.net, ot@iki.fi 2Department of Computing Science, University of Alberta |
| Pseudocode | No | The paper describes algorithms (CFR, CFR+) in textual form but does not provide structured pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide an explicit statement about releasing source code for the described methodology or a link to a code repository. |
| Open Datasets | No | The paper focuses on solving a game (Heads-Up Limit Texas Hold em, Rhode Island hold em) rather than using a pre-existing dataset with public access. It defines the game environment itself. |
| Dataset Splits | No | The paper focuses on solving a game rather than using a dataset with predefined train/validation/test splits in the traditional machine learning sense. Performance is measured by exploitability and convergence over iterations. |
| Hardware Specification | No | The paper mentions '4800 CPUs' and 'a high-performance cluster' provided by 'Calcul Qu ebec, Westgrid, and Compute Canada' but does not specify exact CPU models, GPU models, or other detailed hardware specifications. |
| Software Dependencies | No | The paper describes algorithmic and engineering details but does not list specific software dependencies with version numbers (e.g., Python, PyTorch, specific solvers). |
| Experiment Setup | Yes | In Figure 1c, we demonstrate the first part of this tradeoff in Rhode Island hold em. Each curve shows the convergence of the CFR+ average strategy when the regret values use a scaling parameter from the set: {0.25, 0.5, 0.75, 1, 1.5, 2, 4, 8, 16, 32, 64}. |