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 Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..
Regret Transfer and Parameter Optimization
Authors: Noam Brown, Tuomas Sandholm
AAAI 2014 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We present experiments in no-limit Leduc Hold em and nolimit Texas Hold em to optimize bet sizing. This amounts to the first action abstraction algorithm (algorithm for selecting a small number of discrete actions to use from a continuum of actions a key preprocessing step for solving large games using current equilibrium-finding algorithms) with convergence guarantees for extensive-form games. |
| Researcher Affiliation | Academia | Noam Brown Robotics Institute Carnegie Mellon University EMAIL Tuomas Sandholm Computer Science Department Carnegie Mellon University EMAIL |
| Pseudocode | Yes | Algorithm 1 Parameter optimization in two-player zero-sum games |
| Open Source Code | No | The paper does not provide concrete access to source code for the methodology described. |
| Open Datasets | Yes | We use Leduc hold em poker (Southey et al. 2005) as the test problem here. It has become a common testbed because the game tree is rather large, but small enough that exploitability of a strategy can be computed, and thereby solution quality can be measured. |
| Dataset Splits | No | The paper does not provide specific dataset split information (e.g., percentages, sample counts) for training, validation, or testing. |
| Hardware Specification | No | The paper mentions |
| Software Dependencies | No | The paper mentions using the |
| Experiment Setup | Yes | We used a learning rate ls = s 3 4 , α = 50, and K = 100. We conducted three runs of the algorithm, starting from three different initial values for θ2, respectively. |