CCL: Collaborative Curriculum Learning for Sparse-Reward Multi-Agent Reinforcement Learning via Co-evolutionary Task Evolution

📅 2025-05-08
📈 Citations: 1
Influential: 0
📄 PDF

career value

208K/year
🤖 AI Summary
In multi-agent reinforcement learning (MAS) under sparse rewards, training inefficiency and policy fragility arise from delayed feedback and difficulty in sharing experience across agents. To address these challenges, this paper proposes a collaborative curriculum learning framework. Its key contributions are: (1) a multidimensional curriculum design jointly modulating task difficulty, agent count, and environmental complexity; (2) a variational evolutionary algorithm for automated subtask generation; and (3) a co-evolutionary mechanism integrating agent policy optimization with environmental model learning. The framework unifies curriculum learning, variational evolution, MAS, and environment modeling. Evaluated on five cooperative benchmarks—including MPE and Hide-and-Seek—our method achieves significant improvements over state-of-the-art approaches: 2.1× faster convergence on average and an 18.7% increase in success rate, demonstrating both effectiveness and generalizability.

Technology Category

Application Category

📝 Abstract
Sparse reward environments pose significant challenges in reinforcement learning, especially within multi-agent systems (MAS) where feedback is delayed and shared across agents, leading to suboptimal learning. We propose Collaborative Multi-dimensional Course Learning (CCL), a novel curriculum learning framework that addresses this by (1) refining intermediate tasks for individual agents, (2) using a variational evolutionary algorithm to generate informative subtasks, and (3) co-evolving agents with their environment to enhance training stability. Experiments on five cooperative tasks in the MPE and Hide-and-Seek environments show that CCL outperforms existing methods in sparse reward settings.
Problem

Research questions and friction points this paper is trying to address.

Addresses sparse reward challenges in multi-agent reinforcement learning
Develops co-evolutionary task evolution for better agent training
Improves learning via refined intermediate tasks and subtasks
Innovation

Methods, ideas, or system contributions that make the work stand out.

Refines intermediate tasks for individual agents
Uses variational evolutionary algorithm for subtasks
Co-evolves agents with environment for stability