A new framework for playing and learning board games.
problem Tackling the tedious and repetitive aspects of coding for board game AI.
method Developed a generic TD(λ)-n-tuple agent for arbitrary board games. result TD(λ)-n-tuple outperforms other generic agents on various games. IGGP learns game rules from varying quality game play, finding no overall trend.
problem Learn game rules from varying quality game play.
method Used Sancho's intelligent game traces and ILP systems (Metagol, Aleph, ILASP) to induce game rules from traces of varying quality and volume.
result No overall trend in accuracy of learned game rules from varying quality and volume of training data.
We introduce TextWorld, a sandbox learning environment for the training and evaluation of RL agents on text-based games. TextWorld is a Python library that handles interactive play-through of text games, as well as backend functions like state tracking and reward assignment. It comes with a curated list of games whose …
Gradient methods converge exponentially in concave network games.
problem Finding Nash equilibria in concave network zero-sum games.
method Gradient Ascent and Optimistic Gradient Ascent analyses.
result Exponential convergence rates in various game settings.
Generalizes region select game to k-colored knot diagrams.
problem Play game on knot diagrams with multiple colors.
method Generalize region select game to k-colored knot diagrams. result Generalization of the region select game to k-colored knot diagrams. Gradient-descent-ascent dynamics can exhibit various behaviors in non-convex non-concave games.
problem Gradient-descent-ascent dynamics in non-convex non-concave games can lead to recurrent behavior and spurious equilibria.
method Combines optimization theory, game theory, and dynamical systems.
result Gradient-descent-ascent dynamics can exhibit Poincaré recurrence and converge to spurious equilibria.
Gradient Descent Ascent converges to von-Neumann solution in hidden zero-sum games.
problem Understanding dynamics of zero-sum games with hidden structure.
method Gradient Descent Ascent applied to hidden zero-sum games with specific convex-concave structure.
result Gradient Descent Ascent converges to von-Neumann solution in strictly convex-concave hidden games.
This paper tackles learning Stackelberg equilibrium in asymmetric games efficiently from noisy samples.
problem Learning Stackelberg equilibrium in asymmetric, general-sum games efficiently from noisy samples.
method The paper initiates the theoretical study of sample-efficient learning of the Stackelberg equilibrium in bandit feedback setting.
result Sharp positive results on sample-efficient learning of Stackelberg equilibrium with value optimal up to a fundamental gap identified.
Paper presents content-based models for game recommendation in cold start scenarios.
problem Cold start problem in game recommendation where new games and players have no historical data.
method Uses survey data to develop content-based interaction models that generalize to new games, players, and both.
result Content models outperform collaborative filtering in predicting new interactions.
The existence of stationary Markov perfect equilibria in stochastic games is shown under a general condition called "(decomposable) coarser transition kernels". This result covers various earlier existence results on correlated equilibria, noisy stochastic games, stochastic games with finite actions and state-independe…
Improved RL for TBGs by pruning irrelevant tokens and bootstrapping.
problem RL methods fail to generalize in TBGs with small data.
method CREST for irrelevant token removal, bootstrapped Q-learning.
result Improved generalization in unseen TextWorld games.
Introduces SM-games to analyze machine learning interactions.
problem Lack of understanding and control in n-player games.
method Introduces SM-games with pairwise zero-sum interactions.
result SM-games are amenable to first-order optimization methods.
Combinatorial two-player games have recently been applied to knot theory. Examples of this include the Knotting-Unknotting Game and the Region Unknotting Game, both of which are played on knot shadows. These are turn-based games played by two players, where each player has a separate goal to achieve in order to win the…
Deep RL fails on deceptive games, revealing algorithm weaknesses.
problem Characterizing and understanding failures of deep reinforcement learning.
method Testing A2C on four deceptive games using a game framework.
result Deep RL fails in specific ways that differ from planning-based agents.
Paper proposes using creative ML for game design.
problem Lack of creative ML in game design.
method Leverage existing creative ML systems for game content creation.
result Illustrates how creative ML can inform new game design systems.
In this paper we study the nonzero-sum Dynkin game in continuous time which is a two player non-cooperative game on stopping times. We show that it has a Nash equilibrium point for general stochastic processes. As an application, we consider the problem of pricing American game contingent claims by the utility maximiza…
Just as war is sometimes fallaciously represented as a zero sum game -- when in fact war is a negative sum game - stock market trading, a positive sum game over time, is often erroneously represented as a zero sum game. This is called the "zero sum fallacy" -- the erroneous belief that one trader in a stock market exch…
Policy-gradient algorithms fail to converge to Nash equilibria in continuous state and action space games.
problem Policy-gradient algorithms lack convergence guarantees in multi-agent continuous state and action space games.
method Analysis of gradient-play in linear quadratic games, showing non-convexity and counterexamples.
result Policy-gradient algorithms can avoid Nash equilibria in certain continuous state and action space games.
Simplified NFT games discussed with methods for extracting value.
problem Issues influencing NFT games' structure and stability.
method Three methods for extracting value from NFT games.
result Various design constraints and mutual beneficial games.
Unified framework for Bayesian and Frequentist statistics.
problem Embedding Bayesian statistics within a broader decision-making framework.
method Game theory and statistical analysis.
result Statistical games unify Bayesian and Frequentist statistics.
New tools understand and control dynamics in n-player differentiable games.
problem Understanding and controlling the behavior of gradient-based methods in games.
method Developed new tools to understand and control the dynamics in n-player differentiable games, decomposing the game Jacobian into symmetric and antisymmetric components.
result Motivated Symplectic Gradient Adjustment (SGA) algorithm for finding stable fixed points in differentiable games.
A game theory study examines gradual concessions in variable contribution games under uncertainty.
problem Gradualism in contribution games due to free rider effect.
method Stochastic game analysis of variable contribution games, extending Nerlove-Arrow model.
result Equilibrium characterized by regular control strategies leading to gradual concession.
The paper explores how regularization can lead to convergence in imperfect information games.
problem Finding equilibrium in imperfect information games with imperfect information.
method Investigates Follow the Regularized Leader dynamics and how adding a regularization term can lead to strong convergence guarantees.
result The approach leads to algorithms that converge exactly to the Nash equilibrium in imperfect information games.
We treat the boundary of the union of blocks in the Jenga game as a surface with a polyhedral structure and consider its genus. We generalize the game and determine the maximum genus of the generalized game.
The paper extends game theory using Hodge theory on graphs.
problem Generalizing Shapley's value allocation formula for cooperative games on graphs.
method Connecting stochastic path integrals to Hodge-theoretic Poisson's equations on graphs.
result The value allocation operator is the solution to Poisson's equation in combinatorial Hodge theory.
Paper proposes a game-theoretic approach to generate unlearnable examples.
problem Generating imperceptible perturbations to degrade deep learning models.
method Formulated as a Stackelberg game, proposing a novel attack method GUE.
result GUE effectively poisons models with minimal training data and generalizes well.
Paper tackles hidden game problem in AI alignment and language games.
problem Hidden game problem in AI alignment and language games.
method Developed a composition of regret minimization techniques to discover and exploit hidden structures.
result Achieved optimal external and swap regret bounds for rapid convergence to correlated equilibria.
AEC Games model represents software MARL environments better than POSGs.
problem POSGs are conceptually unsuitable for software MARL environments.
method Introduced AEC Games model as an equivalent to POSGs.
result AEC Games model is more representative of software MARL environments.
Novel approach to Nash equilibrium in mean-field stochastic games with operator resolvents.
problem Finding Nash equilibrium in mean-field stochastic games with mean-field interaction.
method Proposed a novel approach to derive Nash equilibrium semi-explicitly using operator resolvents and stochastic Fredholm equations.
result Equilibrium of the N-player game converges to mean-field equilibrium, and ε-Nash equilibrium derived as a by-product. The paper proposes a method to learn continuous-action graphical games from perturbed equilibria.
problem Learning the exact structure of continuous-action graphical games from limited data.
method A ℓ12− block regularized method to recover the graphical game structure. result The method recovers the exact structure of the graphical game under certain conditions.
Games generalize the single-objective optimization paradigm by introducing different objective functions for different players. Differentiable games often proceed by simultaneous or alternating gradient updates. In machine learning, games are gaining new importance through formulations like generative adversarial netwo…
The paper uses linear function approximators to bias MCTS for general games.
problem Improving MCTS playing strength for general games.
method Using linear function approximators with local features for self-play training.
result Significantly improved playing strength in multiple board games.
Paper models game theory for defending against data poisoning attacks.
problem Defending against data poisoning attacks using game theory.
method Modeling attacker-defender game, proving non-existence of pure Nash Equilibrium, proposing mixed strategy approach, and developing an algorithm to approximate Nash Equilibrium.
result Demonstrated effectiveness of mixed strategy defense in experiments.
In this paper we study the continuum time dynamics of a stock in a market where agents behavior is modeled by a Minority Game and a Grand Canonical Minority Game. The dynamics derived is a generalized geometric Brownian motion; from the Black & Scholes formula the calibration of both the Minority Game and the Grand Can…
Efficiently identifies best algorithms for game tasks.
problem Selecting optimal algorithms for game tasks efficiently.
method Best arm identification for multi-armed bandits with confidence intervals.
result Significantly improved performance in simple regret and error probability.
A new algorithm calculates optimal strategies for two-player zero-sum games.
problem Computing the optimal strategies for two-player zero-sum games.
method Extending successive relaxation to two-player zero-sum games and developing a generalized minimax Q-learning algorithm.
result The proposed algorithm converges and effectively computes optimal strategies.
We introduce CSE for MLSF games and devise online learning algorithms for achieving no-external Stackelberg-regret.
problem Learning equilibrium in leader-follower games with noisy bandit feedback.
method Proposed Correlated Stackelberg Equilibrium (CSE) and online learning algorithms balancing exploration and exploitation.
result Achieves no-external Stackelberg-regret, converging to approximate CSE.
Study Nash equilibrium in non-zero-sum game with Bermudan strategies.
problem Optimizing pay-offs in non-linear non-zero-sum games.
method Recursive construction to find Nash equilibrium.
result Existence of Nash equilibrium in non-zero-sum game.
Neural operators approximate Stackelberg game solutions.
problem Intractability of follower's best-response operator in dynamic Stackelberg games.
method Used attention-based neural operators to approximate the best-response operator.
result Approximate best-response operator yields close game value.
Algorithm solves online binary classification and infinite games using ERM oracle.
problem Online learning and solving infinite games with computationally inefficient oracles.
method Proposes an algorithm relying solely on ERM oracle calls for online binary classification and nonparametric games.
result Achieves finite and sublinearly growing regret in various settings.
In this expository paper we illustrate the generality of game theoretic probability protocols of Shafer and Vovk (2001) in finite-horizon discrete games. By restricting ourselves to finite-horizon discrete games, we can explicitly describe how discrete distributions with finite support and the discrete pricing formulas…
Reinforcement learning improves game level design.
problem Creating high-quality game levels with limited examples.
method Transforming level design into a Markov decision process and training with reinforcement learning.
result Trained reinforcement learning agents can generate high-quality levels quickly.
Last-iterate guarantees for learning in co-coercive games under noisy feedback.
problem Learning in co-coercive games with noisy feedback.
method Vanilla stochastic gradient descent with a new noise model.
result Last-iterate bound of order O(log(t)/t1/3) for co-coercive games. Understanding player behavior is fundamental in game data science. Video games evolve as players interact with the game, so being able to foresee player experience would help to ensure a successful game development. In particular, game developers need to evaluate beforehand the impact of in-game events. Simulation opti…
Paper resolves bias in ALFT training using generalized alignment games.
problem Systematic bias in estimating logarithmic rewards from small batches.
method Generalized Distributional Alignment Games, U-statistics, minimax polynomial estimators, Variance-Optimal Augmented Polynomial Optimization Program (AQP) Estimator.
result Proves optimal bias and accelerated convergence in ALFT training.
Paper withdrawn; AI game behavior needs diversity.
problem Creating varied human-like playing styles in games.
method Evolutionary multi-objective deep reinforcement learning.
result Generated diverse AI behaviors for games.
Gradient methods solve Stackelberg games in high-dimensional, continuous decision spaces.
problem Solving Stackelberg games with continuous, high-dimensional decisions.
method Gradient methods for searching numerical solutions.
result Time and space scalability of gradient methods discussed.
Study Nash equilibria in mean field portfolio games with consumption.
problem Finding Nash equilibria in mean field portfolio games with consumption.
method Established a correspondence between equilibria and solutions to FBSDEs, using martingale and dynamic programming principles.
result Proved the uniqueness of Nash equilibrium in closed form under certain conditions.