Agent Environment Cycle Games

09/28/2020
by   Justin K. Terry, et al.
1

Partially Observable Stochastic Games (POSGs), are the most general model of games used in Multi-Agent Reinforcement Learning (MARL), modeling actions and observations as happening sequentially for all agents. We introduce Agent Environment Cycle Games (AEC Games), a model of games based on sequential agent actions and observations. AEC Games can be thought of as sequential versions of POSGs, and we prove that they are equally powerful. We argue conceptually and through case studies that the AEC games model is useful in important scenarios in MARL for which the POSG model is not well suited. We additionally introduce "cyclically expansive curriculum learning," a new MARL curriculum learning method motivated by the AEC games model. It can be applied "for free," and experimentally we show this technique to achieve up to 35.1 on average.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 6

01/23/2019

The Multi-Agent Reinforcement Learning in MalmÖ (MARLÖ) Competition

Learning in multi-agent scenarios is a fruitful research direction, but ...
07/17/2021

Implicit Communication as Minimum Entropy Coupling

In many common-payoff games, achieving good performance requires players...
11/23/2015

MazeBase: A Sandbox for Learning from Games

This paper introduces MazeBase: an environment for simple 2D games, desi...
06/25/2019

On Multi-Agent Learning in Team Sports Games

In recent years, reinforcement learning has been successful in solving v...
05/26/2021

Finding optimal strategies in sequential games with the novel selection monad

The recently discovered monad, Tx = Selection (x -> r) -> r, provides an...
11/20/2018

Stable Opponent Shaping in Differentiable Games

A growing number of learning methods are actually games which optimise m...
This week in AI

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