Non-Myopic Learning in Repeated Stochastic Games

09/30/2014
by   Jacob W. Crandall, et al.
0

This paper addresses learning in repeated stochastic games (RSGs) played against unknown associates. Learning in RSGs is extremely challenging due to their inherently large strategy spaces. Furthermore, these games typically have multiple (often infinite) equilibria, making attempts to solve them via equilibrium analysis and rationality assumptions wholly insufficient. As such, previous learning algorithms for RSGs either learn very slowly or make extremely limiting assumptions about the game structure or associates' behaviors. In this paper, we propose and evaluate the notion of game abstraction by experts (Gabe) for two-player general-sum RSGs. Gabe reduces an RSG to a multi-armed bandit problem, which can then be solved using an expert algorithm. Gabe maintains many aspects of the original game, including security and Pareto optimal Nash equilibria. We demonstrate that Gabe substantially outperforms existing algorithms in many scenarios.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/11/2023

On the Nash Equilibria of a Simple Discounted Duel

We formulate and study a two-player static duel game as a nonzero-sum di...
research
01/10/2022

Multiplayer Performative Prediction: Learning in Decision-Dependent Games

Learning problems commonly exhibit an interesting feedback mechanism whe...
research
07/28/2021

Efficient Episodic Learning of Nonstationary and Unknown Zero-Sum Games Using Expert Game Ensembles

Game theory provides essential analysis in many applications of strategi...
research
02/21/2023

Partial-Information Q-Learning for General Two-Player Stochastic Games

In this article we analyze a partial-information Nash Q-learning algorit...
research
03/19/2022

Incentive Compatibility in Two-Stage Repeated Stochastic Games

We address the problem of mechanism design for two-stage repeated stocha...
research
08/03/2022

Additive Security Games: Structure and Optimization

In this work, we provide a structural characterization of the possible N...
research
03/15/2012

Automated Planning in Repeated Adversarial Games

Game theory's prescriptive power typically relies on full rationality an...

Please sign up or login with your details

Forgot password? Click here to reset