arXiv research

DefogGAN predicts hidden RTS game information to aid strategic decision-making.

A large body of research is currently investigating on the connection between machine learning and game theory. In this work, game theory notions are injected into a preference learning framework. Specifically, a preference learning problem is seen as a two-players zero-sum game. An algorithm is proposed to incremental…

We study minority games in efficient regime. By incorporating the utility function and aggregating agents with similar strategies we develop an effective mesoscale notion of state of the game. Using this approach, the game can be represented as a Markov process with substantially reduced number of states with explicitl…

We present a comprehensive study of utility function of the minority game in its efficient regime. We develop an effective description of state of the game. For the payoff function $g(x)=\sgn (x)$ we explicitly represent the game as the Markov process and prove the finitness of number of states. We also demonstrate bou…

Bayesian model improves win probability estimates in soccer.

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 …

Method learns state representations without supervision for Atari games.

We introduce an exploration bonus for deep reinforcement learning methods that is easy to implement and adds minimal overhead to the computation performed. The bonus is the error of a neural network predicting features of the observations given by a fixed randomly initialized neural network. We also introduce a method …

Study explores optimal strategies in games with multiple players and mean-field interactions.

We introduce a simple extension of the minority game in which the market rewards contrarian (resp. trend-following) strategies when it is far from (resp. close to) efficiency. The model displays a smooth crossover from a regime where contrarians dominate to one where trend-followers dominate. In the intermediate phase,…

Improved Zero learning framework wins games like Hex and Havannah.

Paper explains adversarial training's robust overfitting through a minimax game perspective.

New measure of feature influence in classification problems considering feature dependencies.

Study explores reinforcement learning in a complex game environment, analyzing rule inference and policy learning.

We study the relationship between social media output and National Football League (NFL) games, using a dataset containing messages from Twitter and NFL game statistics. Specifically, we consider tweets pertaining to specific teams and games in the NFL season and use them alongside statistical game data to build predic…

CURL uses contrastive learning to improve reinforcement learning performance.

Unified framework for feature-based explanations using ANOVA and game theory.

This paper proposes using a linear function approximator, rather than a deep neural network (DNN), to bias a Monte Carlo tree search (MCTS) player for general games. This is unlikely to match the potential raw playing strength of DNNs, but has advantages in terms of generality, interpretability and resources (time and …

Cross-dimensional neural networks improve AI in Catan game.

Deep reinforcement learning has achieved many recent successes, but our understanding of its strengths and limitations is hampered by the lack of rich environments in which we can fully characterize optimal behavior, and correspondingly diagnose individual actions against such a characterization. Here we consider a fam…

Paper compares fairness measures and feature importance measures using SHAP.

Paper uses VAEAC to estimate Shapley values for complex models with mixed features.

Contributions: Prior studies on education have mostly followed the model of the cross sectional study, namely, examining the pretest and the posttest scores. This paper shows that students' knowledge throughout the intervention can be estimated by time series analysis using a hidden Markov model. Background: Analyzing …

Innovative game theory approach optimizes survival analysis metrics.

New method attributes feature uncertainty in ML models using cooperative game theory.

New RL approach tackles non-linear MDPs without linear assumptions.

A game-theoretic approach selects features by testing their marginal contributions.

The paper simplifies multi-agent RL dynamics in finite-state Markov games using homogenization.

Paper explores alternative cooperative game theory methods for machine learning feature attribution.

A new method uses Shapley values to select important features for classification.

Paper develops efficient algorithms for zero-sum Markov games with general function classes.

Pessimistic model-based algorithm finds Nash equilibria in zero-sum Markov games from offline data.

Humans tend to learn complex abstract concepts faster if examples are presented in a structured manner. For instance, when learning how to play a board game, usually one of the first concepts learned is how the game ends, i.e. the actions that lead to a terminal state (win, lose or draw). The advantage of learning end-…

Develops a deep metric learning approach for detecting bugs in video games.

Activities in reinforcement learning (RL) revolve around learning the Markov decision process (MDP) model, in particular, the following parameters: state values, V; state-action values, Q; and policy, pi. These parameters are commonly implemented as an array. Scaling up the problem means scaling up the size of the arra…

Shapley values for feature importance lead to mathematical and practical issues.

Study improves $L^{\infty}$ estimates and extreme value behavior in stochastic differential games.

We consider a zero-sum stochastic differential controller-and-stopper game in which the state process is a controlled diffusion evolving in a multi-dimensional Euclidean space. In this game, the controller affects both the drift and the volatility terms of the state process. Under appropriate conditions, we show that t…

Algorithm learns robust equilibrium in online Markov games with interactive data.

Paper studies optimal tracking portfolio in mean field game of large fund competition.

Deep RL improves Diplomacy performance, outperforming previous methods.

Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrins…

Learning an effective representation for high-dimensional data is a challenging problem in reinforcement learning (RL). Deep reinforcement learning (DRL) such as Deep Q networks (DQN) achieves remarkable success in computer games by learning deeply encoded representation from convolution networks. In this paper, we pro…

This paper gives a critical account of the minority game literature. The minority game is a simple congestion game: players need to choose between two options, and those who have selected the option chosen by the minority win. The learning model proposed in this literature seems to differ markedly from the learning mod…

A new algorithm calculates optimal strategies for two-player zero-sum games.

Consider a two-player zero-sum stochastic game where the transition function can be embedded in a given feature space. We propose a two-player Q-learning algorithm for approximating the Nash equilibrium strategy via sampling. The algorithm is shown to find an $ε$-optimal strategy using sample size linear to the number …

Despite the improved accuracy of deep neural networks, the discovery of adversarial examples has raised serious safety concerns. In this paper, we study two variants of pointwise robustness, the maximum safe radius problem, which for a given input sample computes the minimum distance to an adversarial example, and the …

Paper presents content-based models for game recommendation in cold start scenarios.