Strongly-Typed Agents are Guaranteed to Interact Safely

02/24/2017
by   David Balduzzi, et al.
0

As artificial agents proliferate, it is becoming increasingly important to ensure that their interactions with one another are well-behaved. In this paper, we formalize a common-sense notion of when algorithms are well-behaved: an algorithm is safe if it does no harm. Motivated by recent progress in deep learning, we focus on the specific case where agents update their actions according to gradient descent. The first result is that gradient descent converges to a Nash equilibrium in safe games. The paper provides sufficient conditions that guarantee safe interactions. The main contribution is to define strongly-typed agents and show they are guaranteed to interact safely. A series of examples show that strong-typing generalizes certain key features of convexity and is closely related to blind source separation. The analysis introduce a new perspective on classical multilinear games based on tensor decomposition.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

10/06/2021

O(1/T) Time-Average Convergence in a Generalization of Multiagent Zero-Sum Games

We introduce a generalization of zero-sum network multiagent matrix game...
01/12/2022

Safe Equilibrium

The standard game-theoretic solution concept, Nash equilibrium, assumes ...
07/24/2019

Infection-Curing Games over Polya Contagion Networks

We investigate infection-curing games on a network epidemics model based...
10/22/2020

Beyond Lazy Training for Over-parameterized Tensor Decomposition

Over-parametrization is an important technique in training neural networ...
05/28/2019

Competitive Gradient Descent

We introduce a new algorithm for the numerical computation of Nash equil...
02/15/2018

The Mechanics of n-Player Differentiable Games

The cornerstone underpinning deep learning is the guarantee that gradien...
03/08/2022

COLA: Consistent Learning with Opponent-Learning Awareness

Learning in general-sum games can be unstable and often leads to sociall...
This week in AI

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