Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets
in Chess
- URL: http://arxiv.org/abs/2009.04374v2
- Date: Tue, 15 Sep 2020 16:11:34 GMT
- Title: Assessing Game Balance with AlphaZero: Exploring Alternative Rule Sets
in Chess
- Authors: Nenad Toma\v{s}ev, Ulrich Paquet, Demis Hassabis and Vladimir Kramnik
- Abstract summary: 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.
- Score: 5.3524101179510595
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: It is non-trivial to design engaging and balanced sets of game rules. Modern
chess has evolved over centuries, but without a similar recourse to history,
the consequences of rule changes to game dynamics are difficult to predict.
AlphaZero provides an alternative in silico means of game balance assessment.
It is a system that can learn near-optimal strategies for any rule set from
scratch, without any human supervision, by continually learning from its own
experience. In this study we use AlphaZero to creatively explore and design new
chess variants. There is growing interest in chess variants like Fischer Random
Chess, because of classical chess's voluminous opening theory, the high
percentage of draws in professional play, and the non-negligible number of
games that end while both players are still in their home preparation. We
compare nine other variants that involve atomic changes to the rules of chess.
The changes allow for novel strategic and tactical patterns to emerge, while
keeping the games close to the original. 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. Qualitatively, several
variants are very dynamic. An analytic comparison show that pieces are valued
differently between variants, and that some variants are more decisive than
classical chess. Our findings demonstrate the rich possibilities that lie
beyond the rules of modern chess.
Related papers
- 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) - All by Myself: Learning Individualized Competitive Behaviour with a
Contrastive Reinforcement Learning optimization [57.615269148301515]
In a competitive game scenario, a set of agents have to learn decisions that maximize their goals and minimize their adversaries' goals at the same time.
We propose a novel model composed of three neural layers that learn a representation of a competitive game, learn how to map the strategy of specific opponents, and how to disrupt them.
Our experiments demonstrate that our model achieves better performance when playing against offline, online, and competitive-specific models, in particular when playing against the same opponent multiple times.
arXiv Detail & Related papers (2023-10-02T08:11:07Z) - AlphaZero Gomoku [9.434566356382529]
We broaden the use of AlphaZero to Gomoku, an age-old tactical board game also referred to as "Five in a Row"
Our tests demonstrate AlphaZero's versatility in adapting to games other than Go.
arXiv Detail & Related papers (2023-09-04T00:20:06Z) - Statistical analysis of chess games: space control and tipping points [0.0]
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)
arXiv Detail & Related papers (2023-04-22T14:54:34Z) - ApproxED: Approximate exploitability descent via learned best responses [61.17702187957206]
We study the problem of finding an approximate Nash equilibrium of games with continuous action sets.
We propose two new methods that minimize an approximation of exploitability with respect to the strategy profile.
arXiv Detail & Related papers (2023-01-20T23:55:30Z) - Finding mixed-strategy equilibria of continuous-action games without
gradients using randomized policy networks [83.28949556413717]
We study the problem of computing an approximate Nash equilibrium of continuous-action game without access to gradients.
We model players' strategies using artificial neural networks.
This paper is the first to solve general continuous-action games with unrestricted mixed strategies and without any gradient information.
arXiv Detail & Related papers (2022-11-29T05:16:41Z) - Parallel repetition of local simultaneous state discrimination [12.984519159674525]
Local simultaneous state discrimination is a recently introduced problem in quantum information processing.
We investigate the advantage of no-signalling strategies over classical ones.
We show numerically that for three players and binary values, no-signalling strategies cannot provide any improvement over classical ones.
arXiv Detail & Related papers (2022-11-11T19:33:46Z) - Mastering the Game of Stratego with Model-Free Multiagent Reinforcement
Learning [86.37438204416435]
Stratego is one of the few iconic board games that Artificial Intelligence (AI) has not yet mastered.
Decisions in Stratego are made over a large number of discrete actions with no obvious link between action and outcome.
DeepNash beats existing state-of-the-art AI methods in Stratego and achieved a yearly (2022) and all-time top-3 rank on the Gravon games platform.
arXiv Detail & Related papers (2022-06-30T15:53:19Z) - 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) - Generating Diverse and Competitive Play-Styles for Strategy Games [58.896302717975445]
We propose Portfolio Monte Carlo Tree Search with Progressive Unpruning for playing a turn-based strategy game (Tribes)
We show how it can be parameterized so a quality-diversity algorithm (MAP-Elites) is used to achieve different play-styles while keeping a competitive level of play.
Our results show that this algorithm is capable of achieving these goals even for an extensive collection of game levels beyond those used for training.
arXiv Detail & Related papers (2021-04-17T20:33:24Z) - Learning to Play Sequential Games versus Unknown Opponents [93.8672371143881]
We consider a repeated sequential game between a learner, who plays first, and an opponent who responds to the chosen action.
We propose a novel algorithm for the learner when playing against an adversarial sequence of opponents.
Our results include algorithm's regret guarantees that depend on the regularity of the opponent's response.
arXiv Detail & Related papers (2020-07-10T09:33:05Z)
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.