Friend-or-Foe Q-learning in General-Sum Games

Rational and Convergent Model-Free Adaptive Learning for Team Markov Games1

In this paper, we address multi-agent decision problems where all agents share a common goal. This class of problems is suitably modeled using finite-state Markov games with identical interests. We tackle the problem of coordination and contribute a new algorithm, coordinated Qlearning (CQL). CQL combines Q-learning with biased adaptive play, a coordination mechanism based on the principle of f...

Kant: Friend or Foe of the Believer? Plantinga and Other American Christian Responses to Kant's Epistemology

Friend or foe?: detecting an opponent's attitude in normal form games

We study the problem of achieving cooperation between two self-interested agents that play a sequence of different randomly generated normal form games. The agent learns how much the opponent is willing to cooperate and reciprocates. We present empirical results that show that both agents benefit from cooperation and that a small number of games is sufficient to learn the cooperation level of t...

Apocrine Metaplasia in Intraductal Papilloma with Foci of DCIS: A Friend or Foe?

Malignant papillary neoplasms of the breast comprise a number of microscopically distinct lesions, where apocrine metaplasia is commonly found in papillomas compared to other papillary lesions including papillary carcinomas. However, association of apocrine metaplasia in papilloma with Ductal Carcinoma in Situ (DCIS) is not very well defined. The lesions with apocrine metaplasia are not only di...

Correlated Q-Learning

Recently, there have been several attempts to design multiagent learning algorithms that learn equilibrium policies in general-sum Markov games, just as Q-learning learns optimal policies in Markov decision processes. This paper introduces correlated-Q learning, one such algorithm. The contributions of this paper are twofold: (i) We show empirically that correlated-Q learns correlated equilibri...