日本フィジカルAI新聞

世界のフィジカルAIを、日本語で。

マルチエージェント強化学習arXiv:2410.17690

ポテンシャルゲームと低ランク政策構造によるマルチエージェント到達回避MDP

Multi-agent Reach-avoid MDP via Potential Games and Low-rank Policy Structure

シェア:XThreadsFacebookLINEはてブBluesky

マルチエージェント到達回避MDPを局所フィードバック政策で解き、ポテンシャルゲーム構造を利用して通信・メモリ・計算量を削減しつつ最適解に近い性能を達成する手法を提案。

著者: Adam Casselman, Abraham P. Vinod, Sarah H. Q. Li

分類: eess.SY, cs.GT, cs.MA, cs.RO, cs.SY

原文アブストラクト

We optimize finite horizon multi-agent reach-avoid Markov decision process (MDP) via \emph{local feedback policies}. The global feedback policy solution yields global optimality but its communication complexity, memory usage and computation complexity scale exponentially with the number of agents. We mitigate this exponential dependency by restricting the solution space to local feedback policies and show that local feedback policies are rank-one factorizations of global feedback policies, which provides a principled approach to reducing communication complexity and memory usage. Additionally, by demonstrating that multi-agent reach-avoid MDPs over local feedback policies has a potential game structure, we show that iterative best response is a tractable multi-agent learning scheme with guaranteed convergence to deterministic Nash equilibrium, and derive each agent's best response via multiplicative dynamic program (DP) over the joint state space. Numerical simulations across different MDPs and agent sets show that the peak memory usage and offline computation complexity are significantly reduced while the approximation error to the optimal global reach-avoid objective is maintained.

関連論文

  1. 1Boston Dynamics、車輪付きAtlasの研究試作機を紹介研究・技術
  2. 2newmoとKDDIが資本業務提携 2028年に堺市で自動運転タクシー商用化目指す提携・買収
  3. 3NVIDIA、CoRLでGR00T 2とIsaac Lab 3.0を発表新製品・発表
  4. 4GXOとApptronik、Apolloの物流現場試験を拡大 最大1,000台の展開を構想量産・展開
  5. 5Google DeepMind、ロボット向けAIを発表新製品・発表

PR・アフィリエイト広告

OZ GAMING(GPU搭載BTOゲーミングPC)

OZ GAMING(GPU搭載BTOゲーミングPC)の公式広告バナーOZ GAMINGで完成品PCを見る ↗
PR本紙発行元 EmplifAI