Introduction to the special issue on learning and computational game theory

  title={Introduction to the special issue on learning and computational game theory},
  author={Amy Greenwald and Michael L. Littman},
  journal={Machine Learning},
Game theory is concerned with the decision making of utility-maximizing individuals in their interactions with one another and their environment. From its earliest days of study, researchers have recognized the important relationship between game theory and learning— using experience from past play to guide future decisions. Recently, there has been a surge in research that applies a computational perspective to learning in general-sum games. The editors have been involved with such projects… 

On Similarities between Inference in Game Theory and Machine Learning

The equivalence between inference in game theory and machine learning is elucidated, and an equivalent vocabulary between the two domains is established so as to facilitate developments at the intersection of both fields.

Existence, convergence and efficiency analysis of nash equilibrium and its applications

Game theory deals with strategic interactions among multiple players, where each player tries to maximize/minimize its utility/cost. It has been applied in a broad array of areas such as economics,

Reinforcement Learning Algorithms for Uncertain, Dynamic, Zero-Sum Games

A novel algorithm, based on heterogeneous games of learning automata (HEGLA), as well as algorithms based on model-based and model-free reinforcement learning, are presented as possible approaches to learning the solution Markov equilibrium policies when they are assumed to satisfy the sufficient conditions for existence.

Statistical Prediction of the Outcome of a Noncooperative Game

Conventionally, game theory predicts that the mixed strategy profile of players in a noncooperative game will satisfy some equilibrium concept. Relative probabil- ities of the strategy profiles

Statistical prediction of the outcome of a game

Many machine learning problems involve predicting the joint strategy choice of some goaldirected “players” engaged in a noncooperative game. Conventional game theory predicts that that joint strategy

Multi-Agent Learning II: Algorithms

Neither the problem definition for mutli-agent learning, nor the algorithms offered, follow in a straightforward way from the single-agent case.

Multi-Agent Learning I: Problem Definition

Neither the problem definition for mutli-agent learning, nor the algorithms offered, follow in a straightforward way from the single-agent case.


Lifelong Machine Learning (or Lifelong Learning) is an advanced machine learning paradigm that learns continuously, accumulates the knowledge learned in previous tasks, and uses it to help future

Learning Through Hypothesis Refinement Using Answer Set Programming

A new meta-level learning approach is proposed that overcomes the scalability problem of ASPAL by breaking the learning process up into small manageable steps and using theory revision over the meta- level representation of the hypothesis space to improve the hypothesis computed at each step.

A Game-Based Price Bidding Algorithm for Multi-Attribute Cloud Resource Provision

This work proposes a novel and incentive resource provision model referring to the Quality-of-Service (QoS) and the bidding price, and demonstrates the existence of Nash equilibrium solution set for the formulated game model by assuming that the quantity function of provided resources from every provider is continuous.



Calibrated Learning and Correlated Equilibrium

For each correlated equilibrium there is some calibrated learning rule that the players can use which results in their playing this correlated equilibrium in the limit, and the statistical concept of a calibration is strongly related to the game theoretic concept of correlated equilibrium.

Multiagent learning using a variable learning rate

Bounds for Regret-Matching Algorithms

A general class of learning algorithms, regret-matching algorithms, and a regret-based framework for analyzing their performance in online decision problems are introduced, based on a set Φ of transformations over the set of actions.

Graphical Models for Game Theory

The main result is a provably correct and efficient algorithm for computing approximate Nash equilibria in one-stage games represented by trees or sparse graphs.

Risk analysis of the space shuttle: Pre-Challenger prediction of failure

Abstract The Rogers Commission report on the space shuttle Challenger accident concluded that the accident was caused by a combustion gas leak through a joint in one of the booster rockets, which was

The complexity of computing a Nash equilibrium

It is shown that finding a Nash equilibrium is complete for a class of problems called PPAD, containing several other known hard problems; all problems in PPAD share the same style of proof that every instance has a solution.

If multi-agent learning is the answer, what is the question?