paper-with-me

Papers

Graph-Based Complexity Metrics for Multi-Agent Curriculum Learning: A Validated Approach to Task Ordering in Cooperative Coordination Environments

2025-07-09 · Farhaan Ebadulla, Dharini Hindlatti, Srinivaasan NS, Apoorva VH, Ayman Aftab arxiv

Multi-agent reinforcement learning (MARL) faces significant challenges in task sequencing and curriculum design, particularly for cooperative coordination scenarios. While curriculum learning has demonstrated success in single-agent domains, principled approaches for multi-agent coordination remain limited due to the absence of validated task complexity metrics. This approach presents a graph-based coordination complexity metric that integrates agent dependency entropy, spatial interference patterns, and goal overlap analysis to predict task difficulty in multi-agent environments. The complexity metric achieves strong empirical validation with rho = 0.952 correlation (p < 0.001) between predicted complexity and empirical difficulty determined by random agent performance evaluation. This approach evaluates the curriculum learning framework using MADDPG across two distinct coordination environments: achieving 56x performance improvement in tight coordination tasks (MultiWalker) and demonstrating systematic task progression in cooperative navigation (Simple Spread). Through systematic analysis, coordination tightness emerges as a predictor of curriculum learning effectiveness, where environments requiring strict agent interdependence benefit substantially from structured progression. This approach provides a validated complexity metric for multi-agent curriculum design and establishes empirical guidelines for multi-robot coordination applications.

📄 PDF Abstract BibTeX arXiv:2507.07074

Code (0)

등록된 구현이 없습니다.

Tasks

Multi-agent Reinforcement Learning

Similar Papers 제목 키워드 기반

Curriculum Learning with a Progression Function

2020-08-02 · Andrea Bassich, Francesco Foglino, Matteo Leonetti, Daniel Kudenko

Curriculum Learning for Reinforcement Learning is an increasingly popular technique that involves training an agent on a sequence of intermediate tasks, called a Curriculum, to increase the agent's performance and learni…

reinforcement-learningReinforcement Learning (RL)

Complexity-Guided Curriculum Learning for Text Graphs

2023-11-22 · Nidhi Vakil, Hadi Amiri

Curriculum learning provides a systematic approach to training. It refines training progressively, tailors training to task requirements, and improves generalization through exposure to diverse examples. We present a cur…

Graph Neural Network

Evolutionary Population Curriculum for Scaling Multi-Agent Reinforcement Learning

2020-03-23 · ICLR 2020 1 · Qian Long, Zihan Zhou, Abhibav Gupta, Fei Fang 외

In multi-agent games, the complexity of the environment can grow exponentially as the number of agents increases, so it is particularly challenging to learn good policies when the agent population is large. In this paper…

Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning

2025-06-04 · Nikita Oskolkov, Huzhenyu Zhang, Dmitry Makarov, Dmitry Yudin 외

The 3D scene graph models spatial relationships between objects, enabling the agent to efficiently navigate in a partially observable environment and predict the location of the target object.This paper proposes an origi…

Imitation LearningNavigatereinforcement-learningReinforcement Learning+1

2D-Curri-DPO: Two-Dimensional Curriculum Learning for Direct Preference Optimization

2025-04-10 · Mengyang Li, Zhong Zhang

Aligning large language models with human preferences is crucial for their safe deployment. While Direct Preference Optimization (DPO) offers an efficient alternative to reinforcement learning from human feedback, tradit…

Model Optimization