• Corpus ID: 203610415

Parallel Algorithm for Approximating Nash Equilibrium in Multiplayer Stochastic Games with Application to Naval Strategic Planning

@article{Ganzfried2019ParallelAF,
  title={Parallel Algorithm for Approximating Nash Equilibrium in Multiplayer Stochastic Games with Application to Naval Strategic Planning},
  author={Sam Ganzfried and Conner Laughlin and Charles Morefield},
  journal={ArXiv},
  year={2019},
  volume={abs/1910.00193}
}
Many real-world domains contain multiple agents behaving strategically with probabilistic transitions and uncertain (potentially infinite) duration. Such settings can be modeled as stochastic games. While algorithms have been developed for solving (i.e., computing a game-theoretic solution concept such as Nash equilibrium) two-player zero-sum stochastic games, research on algorithms for non-zero-sum and multiplayer stochastic games is limited. We present a new algorithm for these settings… 
Computing Nash Equilibria in Multiplayer DAG-Structured Stochastic Games with Persistent Imperfect Information
TLDR
This work presents an algorithm for approximating Nash equilibrium in multiplayer general-sum stochastic games with persistent imperfect information that extends throughout game play, and experiments on a 4-player imperfect-information naval strategic planning scenario.
Algorithm for Computing Approximate Nash equilibrium in Continuous Games with Application to Continuous Blotto
TLDR
This work presents a new algorithm for computing Nash equilibrium strategies in continuous games, which applies to two-player zero-sum games and games of imperfect information, and experiments show that the algorithm is able to quickly compute close approximations of Nash equilibrium Strategies for Blotto.
Fictitious Play Outperforms Counterfactual Regret Minimization
TLDR
It is shown that fictitious play leads to improved Nash equilibrium approximation with statistical significance over a variety of game classes and sizes.

References

SHOWING 1-10 OF 28 REFERENCES
Markov Decision Processes: Discrete Stochastic Dynamic Programming
  • M. Puterman
  • Mathematics, Computer Science
    Wiley Series in Probability and Statistics
  • 1994
TLDR
Markov Decision Processes covers recent research advances in such areas as countable state space models with average reward criterion, constrained models, and models with risk sensitive optimality criteria, and explores several topics that have received little or no attention in other books.
Fictitious Play Outperforms Counterfactual Regret Minimization
TLDR
It is shown that fictitious play leads to improved Nash equilibrium approximation with statistical significance over a variety of game classes and sizes.
Deep Counterfactual Regret Minimization
TLDR
Deep Counterfactual Regret Minimization is introduced, a form of CFR that obviates the need for abstraction by instead using deep neural networks to approximate the behavior of CFR in the full game.
Mistakes in games
TLDR
A new concept of "mistake" strategies and actions for strategic-form and extensive-form games has potential applications to cybersecurity, for example detecting whether a human player is illegally using real-time software in online poker.
Superhuman AI for multiplayer poker
TLDR
Pluribus, an AI that is stronger than top human professionals in six-player no-limit Texas hold’em poker, the most popular form of poker played by humans, is presented.
Depth-Limited Solving for Imperfect-Information Games
TLDR
A principled way to conduct depth-limited solving in imperfect-information games by allowing the opponent to choose among a number of strategies for the remainder of the game at the depth limit, which defeats two prior top agents using only a 4-core CPU and 16 GB of memory.
Exclusion Method for Finding Nash Equilibrium in Multiplayer Games
TLDR
This work presents a complete algorithm for finding an e-Nash equilibrium, for arbitrarily small e, in games with more than two players, and it is the first implemented algorithm, to the authors' knowledge, that manages to solve all instances.
Midgame Solving: A New Weapon for Efficient Large-Scale Equilibrium Approximation
  • Kailiang Hu, Sam Ganzfried
  • Computer Science
    2017 IEEE 29th International Conference on Tools with Artificial Intelligence (ICTAI)
  • 2017
TLDR
An agent for no-limit Texas hold 'em is described utilizing the approaches and preliminary experiments against an agent from the Annual Computer Poker Competition that uses popular state-of-the-art techniques such as CFR+.
Endgame Solving in Large Imperfect-Information Games
TLDR
Theoretically, it is shown that endgame solving can produce highly exploitable strategies in some games; however, it can guarantee a low exploitability in certain games where the opponent is given sufficient exploitative power within the endgame.
Computing Solutions in Infinite-Horizon Discounted Adversarial Patrolling Games
TLDR
This work offers a very general model of infinite-horizon discounted adversarial patrolling games, and presents a mixed-integer nonlinear programming (MINLP) formulation for computing optimal randomized policies for the defender, as well as a Mixed-integer linear programming (MILP) formulation to approximate these, with provable quality guarantees.
...
1
2
3
...