Smooth markets: A basic mechanism for organizing gradient-based learners

01/14/2020
by   David Balduzzi, et al.
10

With the success of modern machine learning, it is becoming increasingly important to understand and control how learning algorithms interact. Unfortunately, negative results from game theory show there is little hope of understanding or controlling general n-player games. We therefore introduce smooth markets (SM-games), a class of n-player games with pairwise zero sum interactions. SM-games codify a common design pattern in machine learning that includes (some) GANs, adversarial training, and other recent algorithms. We show that SM-games are amenable to analysis and optimization using first-order methods.

READ FULL TEXT

page 3

page 6

page 8

page 9

page 11

page 12

page 16

page 17

research
12/10/2019

ColosseumRL: A Framework for Multiagent Reinforcement Learning in N-Player Games

Much of recent success in multiagent reinforcement learning has been in ...
research
04/26/2023

With a little help from your friends: semi-cooperative games via Joker moves

This paper coins the notion of Joker games where Player 2 is not strictl...
research
05/29/2019

Extra-gradient with player sampling for provable fast convergence in n-player games

Data-driven model training is increasingly relying on finding Nash equil...
research
02/15/2018

The Mechanics of n-Player Differentiable Games

The cornerstone underpinning deep learning is the guarantee that gradien...
research
08/02/2020

Chaos of Learning Beyond Zero-sum and Coordination via Game Decompositions

Machine learning processes, e.g. ”learning in games”, can be viewed as n...
research
05/01/2023

Human adaptation to adaptive machines converges to game-theoretic equilibria

Adaptive machines have the potential to assist or interfere with human b...
research
05/20/2018

Transitions, Losses, and Re-parameterizations: Elements of Prediction Games

This thesis presents some geometric insights into three different types ...

Please sign up or login with your details

Forgot password? Click here to reset