Scaling Up Multiagent Reinforcement Learning for Robotic Systems: Learn an Adaptive Sparse Communication Graph

Abstract

The complexity of multiagent reinforcement learning (MARL) in multiagent systems increases exponentially with respect to the agent number. This scalability issue prevents MARL from being applied in large-scale multiagent systems. However, one critical feature in MARL that is often neglected is that the interactions between agents are quite sparse. Without exploiting this sparsity structure, existing works aggregate information from all of the agents and thus have a high sample complexity. To address this issue, we propose an adaptive sparse attention mechanism by generalizing a sparsity-inducing activation function. Then a sparse communication graph in MARL is learned by graph neural networks based on this new attention mechanism. Through this sparsity structure, the agents can communicate in an effective as well as efficient way via only selectively attending to agents that matter the most and thus the scale of the MARL problem is reduced with little optimality compromised. Comparative results show that our algorithm can learn an interpretable sparse structure and outperforms previous works by a significant margin on applications involving a large-scale multiagent system.

References in corpus (12)

• Attention-Based Models for Speech Recognition
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Learning a Generic Value-Selection Heuristic Inside a Constraint Programming Solver
• Counterfactual Multi-Agent Policy Gradients
• Mean Field Multi-Agent Reinforcement Learning
• Guided Deep Reinforcement Learning for Swarm Systems
• A Regularized Framework for Sparse and Structured Neural Attention
• Graph Convolutional Reinforcement Learning
• TarMAC: Targeted Multi-Agent Communication
• Graph Policy Gradients for Large Scale Robot Control
• Adaptively Sparse Transformers
• Learning Classifiers with Fenchel-Young Losses: Generalized Entropies, Margins, and Algorithms

Cited by in corpus (1)

• Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning