On Information Asymmetry in Competitive Multi-Agent Reinforcement Learning: Convergence and Optimality

10/21/2020
by   Ezra Tampubolon, et al.
0

In this work, we study the system of interacting non-cooperative two Q-learning agents, where one agent has the privilege of observing the other's actions. We show that this information asymmetry can lead to a stable outcome of population learning, which generally does not occur in an environment of general independent learners. The resulting post-learning policies are almost optimal in the underlying game sense, i.e., they form a Nash equilibrium. Furthermore, we propose in this work a Q-learning algorithm, requiring predictive observation of two subsequent opponent's actions, yielding an optimal strategy given that the latter applies a stationary strategy, and discuss the existence of the Nash equilibrium in the underlying information asymmetrical game.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

11/29/2020

Minimax Sample Complexity for Turn-based Stochastic Game

The empirical success of Multi-agent reinforcement learning is encouragi...
03/13/2018

Decentralised Learning in Systems with Many, Many Strategic Agents

Although multi-agent reinforcement learning can tackle systems of strate...
09/16/2019

Stochastic Dynamic Games in Belief Space

Information gathering while interacting with other agents is critical in...
06/22/2011

Competitive Safety Analysis: Robust Decision-Making in Multi-Agent Systems

Much work in AI deals with the selection of proper actions in a given (k...
12/18/2017

Game-Theoretic Electric Vehicle Charging Management Resilient to Non-Ideal User Behavior

In this paper, an electric vehicle (EV) charging competition, among EV a...
10/29/2016

Multi-agent projective simulation: A starting point

We develop a two-defender (Alice and Bob) invasion game using the method...
07/30/2020

Moody Learners – Explaining Competitive Behaviour of Reinforcement Learning Agents

Designing the decision-making processes of artificial agents that are in...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.