Statistical analysis of chess games: space control and tipping points

• URL: http://arxiv.org/abs/2304.11425v2
• Date: Thu, 27 Apr 2023 06:30:10 GMT
• Title: Statistical analysis of chess games: space control and tipping points
• Authors: Marc Barthelemy
• Abstract summary: We first focus on spatial properties and the location of pieces and show that the number of possible moves during a game is positively correlated with its outcome. We then study heatmaps of pieces and show that the spatial distribution of pieces varies less between human players than with engines (such as Stockfish)
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Moves in chess games are usually analyzed on a case-by-case basis by professional players, but thanks to the availability of large game databases, we can envision another approach of the game. Here, we indeed adopt a very different point of view, and analyze moves in chess games from a statistical point of view. We first focus on spatial properties and the location of pieces and show that the number of possible moves during a game is positively correlated with its outcome. We then study heatmaps of pieces and show that the spatial distribution of pieces varies less between human players than with engines (such as Stockfish): engines seem to use pieces in a very different way as human did for centuries. These heatmaps also allow us to construct a distance between players that characterizes how they use their pieces. In a second part, we focus on the best move and the second best move found by Stockfish and study the difference $\Delta$ of their evaluation. We found different regimes during a chess game. In a `quiet' regime, $\Delta$ is small, indicating that many paths are possible for both players. In contrast, there are also `volatile' regimes characterized by a `tipping point', for which $\Delta$ becomes large. At these tipping points, the outcome could then switch completely depending on the move chosen. We also found that for a large number of games, the distribution of $\Delta$ can be fitted by a power law $P(\Delta)\sim \Delta^{-\beta}$ with an exponent that seems to be universal (for human players and engines) and around $\beta\approx 1.8$. The probability to encounter a tipping point in a game is therefore far from being negligible. Finally, we conclude by mentioning possible directions of research for a quantitative understanding of chess games such as the structure of the pawn chain, the interaction graph between pieces, or a quantitative definition of critical points.

Related papers

• You shall know a piece by the company it keeps. Chess plays as a data for word2vec models [0.0]
  I show how word embeddings (word2vec) can work on chess game texts instead of natural language texts. It's unlikely that these vector models will help engines or people choose the best move.
  arXiv  Detail & Related papers  (2024-07-28T22:12:36Z)
• Imperfect-Recall Games: Equilibrium Concepts and Their Complexity [74.01381499760288]
  We investigate optimal decision making under imperfect recall, that is, when an agent forgets information it once held before. In the framework of extensive-form games with imperfect recall, we analyze the computational complexities of finding equilibria in multiplayer settings.
  arXiv  Detail & Related papers  (2024-06-23T00:27:28Z)
• Predicting User Perception of Move Brilliance in Chess [3.434553688053531]
  We show the first system for classifying chess moves as brilliant. The system achieves an accuracy of 79% (with 50% base-rate), a PPV of 83%, and an NPV of 75%. We show that a move is more likely to be predicted as brilliant, all things being equal, if a weaker engine considers it lower-quality.
  arXiv  Detail & Related papers  (2024-06-14T17:46:26Z)
• The Value of Chess Squares [5.647533385886476]
  Our model takes a triplet (Color, Piece, Square) as an input and calculates a value that measures the advantage/disadvantage of having this piece on this square. Our methods build on recent advances in chess AI, and can accurately assess the worth of positions in a game of chess.
  arXiv  Detail & Related papers  (2023-07-08T20:17:24Z)
• Intransitively winning chess players positions [91.3755431537592]
  The space of relations between winningness of positions of chess players is non-Euclidean. The Zermelo-von Neumann theorem is complemented by statements about possibility vs. impossibility of building pure winning strategies.
  arXiv  Detail & Related papers  (2022-12-11T05:55:05Z)
• Principal Trade-off Analysis [79.16635054977068]
  We show "Principal Trade-off Analysis" (PTA), a decomposition method that embeds games into a low-dimensional feature space. PTA represents an arbitrary two-player zero-sum game as the weighted sum of pairs of 2D feature planes. We demonstrate the validity of PTA on a quartet of games (Kuhn poker, RPS+2, Blotto, and Pokemon)
  arXiv  Detail & Related papers  (2022-06-09T18:16:28Z)
• Collusion Detection in Team-Based Multiplayer Games [57.153233321515984]
  We propose a system that detects colluding behaviors in team-based multiplayer games. The proposed method analyzes the players' social relationships paired with their in-game behavioral patterns. We then automate the detection using Isolation Forest, an unsupervised learning technique specialized in highlighting outliers.
  arXiv  Detail & Related papers  (2022-03-10T02:37:39Z)
• Measuring the Non-Transitivity in Chess [19.618609913302855]
  We quantify the non-transitivity in Chess through real-world data from human players. There exists a strong connection between the degree of non-transitivity and the progression of a Chess player's rating.
  arXiv  Detail & Related papers  (2021-10-22T12:15:42Z)
• Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets in Chess [5.3524101179510595]
  We use AlphaZero to creatively explore and design new chess variants. We compare nine other variants that involve atomic changes to the rules of chess. By learning near-optimal strategies for each variant with AlphaZero, we determine what games between strong human players might look like if these variants were adopted.
  arXiv  Detail & Related papers  (2020-09-09T15:49:14Z)
• Efficient exploration of zero-sum stochastic games [83.28949556413717]
  We investigate the increasingly important and common game-solving setting where we do not have an explicit description of the game but only oracle access to it through gameplay. During a limited-duration learning phase, the algorithm can control the actions of both players in order to try to learn the game and how to play it well. Our motivation is to quickly learn strategies that have low exploitability in situations where evaluating the payoffs of a queried strategy profile is costly.
  arXiv  Detail & Related papers  (2020-02-24T20:30:38Z)
• Learning Zero-Sum Simultaneous-Move Markov Games Using Function Approximation and Correlated Equilibrium [116.56359444619441]
  We develop provably efficient reinforcement learning algorithms for two-player zero-sum finite-horizon Markov games. In the offline setting, we control both players and aim to find the Nash Equilibrium by minimizing the duality gap. In the online setting, we control a single player playing against an arbitrary opponent and aim to minimize the regret.
  arXiv  Detail & Related papers  (2020-02-17T17:04:16Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.