Heterogeneous Multi-robot Reinforcement Learning

Abstract

Cooperative multi-robot tasks can benefit from heterogeneity in the robots' physical and behavioral traits. In spite of this, traditional Multi-Agent Reinforcement Learning (MARL) frameworks lack the ability to explicitly accommodate policy heterogeneity, and typically constrain agents to share neural network parameters. This enforced homogeneity limits application in cases where the tasks benefit from heterogeneous behaviors. In this paper, we crystallize the role of heterogeneity in MARL policies. Towards this end, we introduce Heterogeneous Graph Neural Network Proximal Policy Optimization (HetGPPO), a paradigm for training heterogeneous MARL policies that leverages a Graph Neural Network for differentiable inter-agent communication. HetGPPO allows communicating agents to learn heterogeneous behaviors while enabling fully decentralized training in partially observable environments. We complement this with a taxonomical overview that exposes more heterogeneity classes than previously

Stats

• citations7
• S2 citations—
• github stars0
• HF likes0
• heat score6.77
• arxiv keybettini2023heterogeneous

Related papers

• Cooperative Policy Learning With Pre-trained Heterogeneous Observation Representations (2020)0.00
• Heterogeneous Multi-agent Reinforcement Learning For Zero-shot Scalable Collaboration (2024)6.34
• Enhancing Heterogeneous Multi-agent Cooperation In Decentralized MARL Via Gnn-driven Intrinsic Rewards (2024)0.00
• Halypo: Heterogeneous-agent Lyapunov Policy Optimization For Human-robot Collaboration (2026)0.00
• Heterogeneous-agent Reinforcement Learning (2023)0.00
• Towards Heterogeneous Multi-agent Reinforcement Learning With Graph Neural Networks (2020)6.34
• Learning Heterogeneous Agent Cooperation Via Multiagent League Training (2022)7.16
• Hypermarl: Adaptive Hypernetworks For Multi-agent RL (2024)0.00