Specializing Inter-agent Communication In Heterogeneous Multi-agent Reinforcement Learning Using Agent Class Information

Abstract

Inspired by recent advances in agent communication with graph neural networks, this work proposes the representation of multi-agent communication capabilities as a directed labeled heterogeneous agent graph, in which node labels denote agent classes and edge labels, the communication type between two classes of agents. We also introduce a neural network architecture that specializes communication in fully cooperative heterogeneous multi-agent tasks by learning individual transformations to the exchanged messages between each pair of agent classes. By also employing encoding and action selection modules with parameter sharing for environments with heterogeneous agents, we demonstrate comparable or superior performance in environments where a larger number of agent classes operates.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keymeneghetti2020specializing

Related papers

• Towards Heterogeneous Multi-agent Reinforcement Learning With Graph Neural Networks (2020)6.34
• Universally Expressive Communication In Multi-agent Reinforcement Learning (2022)0.00
• Counterfactual Multi-agent Reinforcement Learning With Graph Convolution Communication (2020)0.00
• A Survey Of Multi-agent Deep Reinforcement Learning With Graph Neural Network-based Communication (2026)0.00
• Modeling Sensorimotor Coordination As Multi-agent Reinforcement Learning With Differentiable Communication (2019)0.00
• Learning Practical Communication Strategies In Cooperative Multi-agent Reinforcement Learning (2022)0.00
• Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations (2020)0.00
• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16