From 72ccde4f0d32b08880f62921b76ea61e40c338a2 Mon Sep 17 00:00:00 2001 From: Rafael Fernandes Cunha <r.f.cunha@rug.nl> Date: Wed, 18 Dec 2024 11:56:54 +0000 Subject: [PATCH] abstract --- README.md | 11 +---------- 1 file changed, 1 insertion(+), 10 deletions(-) diff --git a/README.md b/README.md index eadfca8..39be91e 100644 --- a/README.md +++ b/README.md @@ -7,16 +7,7 @@ This repository contains the C++ implementation accompanying the AAAI-25 confere **"Optimally Solving Simultaneous-Move Dec-POMDPs: The Sequential Central Planning Approach"** -The centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to $\epsilon$-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. - -This paper presents a novel and more scalable alternative, namely the sequential-move centralized training for decentralized execution. -First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. -Next, it proves that $\epsilon$-optimal value functions are piecewise linear and convex in such sufficient sequential-move statistics. -Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. - -Experiments on two- as well as many-agent domains from the literature against $\epsilon$-optimal simultaneous-move solvers confirm the superiority of our novel approach. - -This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems. +The centralized training for decentralized execution paradigm emerged as the state-of-the-art approach to $\epsilon$-optimally solving decentralized partially observable Markov decision processes. However, scalability remains a significant issue. This paper presents a novel and more scalable alternative, namely the sequential-move centralized training for decentralized execution. First, it allows a central planner to reason upon sufficient sequential-move statistics instead of prior simultaneous-move ones. Next, it proves that $\epsilon$-optimal value functions are piecewise linear and convex in such sufficient sequential-move statistics. Finally, it drops the complexity of the backup operators from double exponential to polynomial at the expense of longer planning horizons. Experiments on two- as well as many-agent domains from the literature against $\epsilon$-optimal simultaneous-move solvers confirm the superiority of our novel approach. This paradigm opens the door for efficient planning and reinforcement learning methods for multi-agent systems. ## Overview -- GitLab