Real World Games Look Like Spinning Tops
Authors: Wojciech M. Czarnecki, Gauthier Gidel, Brendan Tracey, Karl Tuyls, Shayegan Omidshafiei, David Balduzzi, Max Jaderberg
NeurIPS 2020 | Conference PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | To empirically validate the spinning top geometry, we consider a selection of two-player zero-sum games available in the Open Spiel library [16]. ... Table 1 summarises the empirical analysis which, for the sake of completeness, includes both Games of Skill and games that are not Games of Skill such as the Disc game [2], a purely transitive Elo game, and the Blotto game. Overall, all real world games results show the hypothesised spinning top geometry. |
| Researcher Affiliation | Industry | Wojciech Marian Czarnecki Deep Mind London Gauthier Gidel Deep Mind London Brendan Tracey Deep Mind London Karl Tuyls Deep Mind Paris Shayegan Omidshafiei Deep Mind Paris David Balduzzi Deep Mind London Max Jaderberg Deep Mind London |
| Pseudocode | No | The paper states "algorithms used (A, C, D, I, J)" are provided in supplementary materials, but no pseudocode or algorithm blocks are present in the main text. |
| Open Source Code | No | The paper does not provide a direct link to open-source code for the described methodology. It mentions "details on implementations of empirical experiments (E, G, H)" in Supplementary Materials, but this is not an explicit statement of code release or a direct link. |
| Open Datasets | No | The paper states it considers "a selection of two-player zero-sum games available in the Open Spiel library [16]" and relies on "empirical game-theoretic analysis, an experimental paradigm that relies on simulation and sampling of strategies to construct abstracted counterparts of complex underlying games". While Open Spiel is a public framework, the paper does not specify a pre-existing public dataset with concrete access information for *the data generated* from these games, but rather describes a *sampling process*. |
| Dataset Splits | No | The paper does not explicitly state training/validation/test dataset splits. It describes a sampling procedure: "First, apply a tree-search method, in the form of Alpha-Beta [22] and MCTS [4] and select a range of parameters that control the transitive strength of these algorithms... Second, for each such strategy we create multiple instances, with varied random number seed... Finally, following strategy sampling, we form an empirical payoff table..." |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., CPU, GPU models, memory) used for running the experiments. It only mentions the software used (Open Spiel). |
| Software Dependencies | No | The paper mentions "Open Spiel library [16]" but does not provide specific version numbers for Open Spiel or any other software dependencies. |
| Experiment Setup | Yes | A simple and intuitive procedure for strategy sampling is as follows. First, apply a tree-search method, in the form of Alpha-Beta [22] and MCTS [4] and select a range of parameters that control the transitive strength of these algorithms (depth of search for Alpha-Beta and number of simulations for MCTS) to ensure coverage of transitive dimension. |