Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in [1].
Revisiting CFR+ and Alternating Updates
Authors: Neil Burch, Matej Moravcik, Martin Schmid
JAIR 2019 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We provide updated proofs to recover the original bound. ... By proving that CFR and CFR+ generate improved strategies, we can give a new correctness proof for CFR+, recovering the original bound on approximation error. ... The original CFR+ convergence proof makes unsupported use of the folk theorem linking regret to exploitability. We re-make the link between regret and exploitability for alternating updates, and provide a corrected CFR+ convergence proof that recovers the original exploitability bound. |
| Researcher Affiliation | Industry | Neil Burch EMAIL Matej Moravcik EMAIL Martin Schmid EMAIL Deep Mind, 5 New Street Square, London, EC4A 3TW |
| Pseudocode | No | The paper does not contain any structured pseudocode or algorithm blocks. It describes algorithms (CFR, CFR+, regret-matching) conceptually and mathematically. |
| Open Source Code | No | The paper does not provide any explicit statement or link regarding the availability of open-source code for the methodology described. |
| Open Datasets | No | The paper is theoretical and focuses on proofs and algorithmic properties for solving imperfect information games. It does not describe experiments performed on any specific dataset nor does it provide concrete access information for any dataset. |
| Dataset Splits | No | The paper is theoretical and does not involve experiments on datasets, therefore, no dataset split information is provided. |
| Hardware Specification | No | The paper is theoretical, providing proofs and algorithmic analysis. It does not describe any experimental setup or specific hardware used for computations. |
| Software Dependencies | No | The paper is theoretical and focuses on mathematical proofs and algorithmic properties rather than implementation details. It does not specify any software dependencies with version numbers. |
| Experiment Setup | No | The paper is theoretical and provides proofs for algorithm convergence. It does not describe any empirical experiments, and therefore, no experimental setup details, hyperparameters, or training configurations are mentioned. |