Graphical potential games extend game theory to networks and machine learning.
problem Extending potential games to network settings.
method Characterizing graphical potential games using probabilistic graphical models.
result Game-playing rules imply agents are in a graphical potential game.
Decentralised optimisation tasks are important components of multi-agent systems. These tasks can be interpreted as n-player potential games: therefore game-theoretic learning algorithms can be used to solve decentralised optimisation tasks. Fictitious play is the canonical example of these algorithms. Nevertheless fic…
End-to-end model predicts multiagent trajectories using game theory and neural nets.
problem Predicting trajectories of interacting agents in complex scenarios.
method Hybrid neural net with game-theoretic reasoning, using implicit layers to map preferences to Nash equilibria.
result Trains an interpretable model that predicts future trajectories and transfers to decision making.
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. New algorithm improves game learning with randomised optimism.
problem Learning in matrix games with unknown payoffs and bandit feedback.
method Integrates evolutionary algorithms into bandit framework for randomised optimism.
result Achieves sublinear regret, outperforming classical methods.
Game theory helps analyze ESOs/EBIs in production and service sectors.
problem Economic incentives affect traditional production/service functions and create intangible capital.
method Uses game theory to analyze interactions in ESO/EBI transactions.
result No perfect Nash Equilibria for two-stage games involving many participants.
Motivated by the recent applications of game-theoretical learning techniques to the design of distributed control systems, we study a class of control problems that can be formulated as potential games with continuous action sets, and we propose an actor-critic reinforcement learning algorithm that provably converges t…
We report on a technique based on multi-agent games which has potential use in the prediction of future movements of financial time-series. A third-party game is trained on a black-box time-series, and is then run into the future to extract next-step and multi-step predictions. In addition to the possibility of identif…
The 1/3 Financial Rule helps prevent household bankruptcy through balanced spending, savings, and debt repayment.
problem Reducing household bankruptcy risk through effective financial planning.
method Mathematical modeling, game theory, behavioral finance, and technological analysis.
result The 1/3 Financial Rule emerges as a robust solution for supporting household financial stability.
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.
The paper explores game-theoretic alignment of LLMs with human preferences, finding limitations and conditions.
problem Aligning LLMs with human preferences using game theory.
method Systematic study of payoff choices in a two-player zero-sum game for desirable alignment properties.
result Impossibility of preference matching in game-theoretic LLM alignment under standard assumptions.
Game theory enhances preference learning, improving feature selection and interpretability.
problem Improving feature selection and interpretability in preference learning.
method Formulates preference learning as a two-player zero-sum game, proposing an algorithm to incrementally add features.
result Demonstrates the convergence of the algorithm and shows its effectiveness in feature selection and interpretability.
Study explores algorithmic collusion in repeated games using various learning dynamics.
problem Understanding algorithmic collusion in repeated games with different learning dynamics.
method Examines Q-learning, gradient learning, and other dynamics in a general repeated game setting. result Characterizes the set of payoff vectors achievable by these dynamics, revealing possibilities for collusion.
This paper improves sample efficiency for learning equilibria in multi-player games.
problem Sample-efficient learning of equilibria in games with many players.
method Designs algorithms for learning CCE and CE with polynomial sample complexity in the number of players.
result First to show polynomial sample complexity for learning CCE and CE in multi-player games.
Interactive game approach extracts action graphs from specialized text.
problem Action graph extraction from specialized procedural text.
method Interpreting procedural text as game instructions, using a learning agent to simulate and execute the procedure.
result Framework complements existing approaches and enables richer learning.
Analyzes gradient-based learning in games, avoiding local Nash equilibria.
problem Analyzes gradient-based learning in competitive games.
method Formulates a general framework and uses dynamical systems theory.
result Characterizes local Nash equilibria avoided by gradient-based learning.
It is now well known that decentralised optimisation can be formulated as a potential game, and game-theoretical learning algorithms can be used to find an optimum. One of the most common learning techniques in game theory is fictitious play. However fictitious play is founded on an implicit assumption that opponents' …
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.
Modeling resource accumulation in a population game to explain wealth distribution.
problem Explaining the distribution of wealth in a population game.
method Modeling resource accumulation as a population game with Hawk-Dove interactions, analyzing fitness/wealth distribution and evolution over time.
result Long-run average fitness/wealth is non-monotonic with resource value, explaining the 'curse of riches'.
Game theory models incentivizes honesty in collaborative learning among competitors.
problem Incentivizing honest updates among competitors in collaborative learning schemes.
method Formulated a game to model interactions, studied two learning tasks, proposed mechanisms to incentivize honest communication.
result Rational clients are incentivized to manipulate their updates, preventing learning; proposed mechanisms ensure comparable learning quality to full cooperation.
New measure of feature influence in classification problems considering feature dependencies.
problem Measuring the influence of features in classification problems with dependencies.
method Developed a new measure based on cooperative game theory, providing axiomatic characterization and demonstrating its equivalence to the Banzhaf-Owen value.
result The proposed influence measure effectively characterizes feature importance in classification problems with feature dependencies.
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.
Hybrid SAC improves RL for video games with discrete, continuous actions.
problem Improving RL performance in video games with practical constraints.
method Extension of Soft Actor-Critic (SAC) for handling discrete, continuous, and parameterized actions.
result Hybrid SAC successfully solves a high-speed driving task and is competitive on parameterized actions benchmarks.
We create real-time geodesic rendering for non-isotropic geometries.
problem Challenging visualization of non-isotropic geometries.
method Novel methods for real-time native geodesic rendering.
result Methods can be applied to visualization, machine learning, and video games.
Study examines large banks' role in interbank markets using game theory.
problem Understanding systemic risk in interbank markets with large banks.
method Mean-field game framework, convex analysis, Monte Carlo simulations.
result Large banks can positively or negatively impact market stability.
Modeling pollution from competing firms using mean-field games.
problem Pollution regulation of competitive firms producing similar goods.
method Developed a mean-field game model with cap-and-trade regulation.
result Explicit solutions found through Riccati differential equations.
Kernel-based mean-field games use MMD penalties for interaction and target costs.
problem Optimizing mean-field games with specific cost functions.
method Kernel structure, random Fourier U-statistics, neural network training.
result Sample-level convergence theorem and rate of convergence proved.
New Shapley values reveal non-linear feature dependencies.
problem Understanding non-linear dependencies in machine learning models.
method Model-independent Shapley values using non-parametric measures of dependence.
result Model-independent Shapley values can uncover non-linear dependencies.
Capsule networks improve AI in complex game environments.
problem Improving AI opponents in advanced game environments.
method Introducing four new game environments, generating training data, and applying CapsNet for Deep Q-Learning.
result CapsNet is a reliable architecture for game AI.
Develops a framework to estimate NBA player salary ROI.
problem Measuring the relative return of player salaries in NBA.
method Five-part framework: GCP measure, SGV calculation, cash flow series, ROI calculation.
result Illustrates framework with 2022-2023 NBA data, showing top and bottom performers.
New approach tackles non-stationary multi-agent games with black-box methods.
problem Challenges in learning equilibria in non-stationary multi-agent systems.
method Versatile black-box approach applicable to various games, including general-sum, potential, and Markov games.
result Achieves optimal regret bounds for non-stationary games, with or without knowledge of total variation.
A new game-theoretic approach balances downside risk with expected reward.
problem Traditional game theory views risk only from the upside perspective, ignoring downside risk.
method Introduces downside risk aware equilibria (DRAE) based on lower partial moments.
result Successfully finds equilibria that balance downside risk with expected reward.
A game-theoretic approach simplifies MBRL design and improves sample efficiency.
problem Designing stable and efficient MBRL algorithms using rich function approximators.
method Develops a game-theoretic framework where MBRL is modeled as a Stackelberg game between policy and model players.
result Proposed algorithms are highly sample efficient and match asymptotic performance of model-free policy gradient.
Proposes a deep learning method for solving complex financial games with delays.
problem Financial modeling with multi-agent interactions and delayed effects.
method Parameterizes controls using recurrent neural networks and trains them with modified fictitious play.
result Demonstrates effectiveness on finance problems with known solutions and new problems with derived Nash equilibria.
Deep neural networks outperform parametric models in predicting customer lifetime value in video games.
problem Predicting the economic value of individual players in free-to-play video games.
method Exploration of deep neural networks and parametric models (Pareto/NBD) for predicting customer lifetime value.
result Convolutional neural networks are the most efficient in predicting the economic value of individual players.
A new method assesses algorithmic fairness using game theory.
problem Evaluating algorithmic fairness without proprietary data.
method Cohort Shapley value, a game-theoretic approach.
result Identifies individual impact of protected attributes.
This work designs secure DSVMs against adversaries using game theory.
problem Adversaries can deceive DSVMs leading to misclassification and misprediction.
method Game-theoretic framework to model DSVM learner and attacker interactions, finding Nash equilibrium.
result DSVM learner is less vulnerable with balanced networks and more training samples.
This paper tackles global Nash equilibrium in non-convex multi-player games.
problem Challenges in finding global Nash equilibrium due to non-convexity.
method Conjugate transformation and variational inequality formulation to prove existence and design algorithms.
result Designs an ODE-based algorithm with exponential convergence rate and proves its effectiveness in practical scenarios.
Fractal neural networks play SimCity and Conway's Game of Life on varying scales.
problem Generalizing agents' performance to larger gameboards than during training.
method Reinforcement learning in a custom environment, using fractal neural networks.
result Agents can generalize to larger gameboards, solving a minigame unsolvable with local strategies.
New algorithms compute approximate variational inference in MRFs using game-theoretic methods.
problem Approximate variational inference in Markov random fields (MRFs).
method Formulations of inference problems in MRFs as correlated equilibria in game-theoretic graphical models.
result Competitive global approach, particularly effective in highly attractive edge-weighted models.
New algorithms for RL in Markov games with independent linear function approximation, breaking the curse of multiagents.
problem Tackles the challenge of learning Markov equilibria in large state space Markov games with multiple agents.
method Proposes independent linear Markov games and designs new algorithms for learning Markov coarse correlated equilibria and Markov correlated equilibria with polynomial sample complexity.
result Breaks the curse of multiagents by achieving sample complexity bounds that scale polynomially with each agent's function class complexity.
Modeling DEX liquidity with heterogeneous LPs and MEV bots.
problem Understanding and predicting the dynamics of decentralized cryptocurrency exchanges.
method Mean-field game approach to model liquidity providers' optimal strategies and interactions.
result Calibrated model produces consistent pool exchange rate dynamics and liquidity evolution.
APAC-Net solves high-dimensional stochastic MFGs using neural networks.
problem High-dimensional stochastic mean-field games.
method Alternating population and control neural networks, parameterizing value and density functions.
result Solves up to 100-dimensional MFG problems.
Improved bounds for online prediction with expert advice.
problem Online prediction with expert advice in finite-horizon games.
method Verification arguments from optimal control theory applied to PDEs to find sub- and supersolutions.
result Explicit bounds for any number of experts and horizon, improving upon previous results.
Q*BERT learns to navigate text-based games by building a knowledge graph.
problem Text-based games have bottlenecks that standard RL agents struggle to overcome.
method Q*BERT learns a knowledge graph and uses intrinsic motivation to detect and overcome bottlenecks.
result Q*BERT outperforms state-of-the-art agents in text games, including Zork.
The paper introduces a new model to improve exotic option pricing.
problem Challenges in pricing exotic options and structured products due to market phenomena.
method Introduces a Diffusion-Conditional Probability Model (DDPM) with a composite loss function and P-Q dynamic game framework.
result The DDPM outperforms traditional models in dynamic games for European and Asian options, but underestimates tail risks.
New approach for adaptive conformal inference using Blackwell's theory.
problem Non-exchangeable environments in sequential conformal inference.
method Reinterpretation of ACI as a game, construction of coverage and efficiency objectives, approachability strategy.
result Algorithm achieves strong theoretical guarantees and practical insights.
A new method solves high-dimensional MFGs using particle-based flow matching.
problem Solving high-dimensional Mean-Field Games (MFGs) is computationally challenging.
method Proposes a particle-based deep Flow Matching (FM) method to update particles and train a flow neural network.
result Proves convergence of the scheme to a stationary point sublinearly and linearly under convexity assumptions.