Hierarchical Policy-gradient Reinforcement Learning For Multi-agent Shepherding Control Of Non-cohesive Targets

Abstract

We propose a decentralized reinforcement learning solution for multi-agent shepherding of non-cohesive targets using policy-gradient methods. Our architecture integrates target-selection with target-driving through Proximal Policy Optimization, overcoming discrete-action constraints of previous Deep Q-Network approaches and enabling smoother agent trajectories. This model-free framework effectively solves the shepherding problem without prior dynamics knowledge. Experiments demonstrate our method's effectiveness and scalability with increased target numbers and limited sensing capabilities.

Stats

• citations0
• S2 citations—
• github stars0
• HF likes0
• heat score0.00
• arxiv keycovone2025hierarchical

Related papers

• Scalable Centralized Deep Multi-agent Reinforcement Learning Via Policy Gradients (2018)0.00
• A Policy Gradient Algorithm For Learning To Learn In Multiagent Reinforcement Learning (2020)0.00
• Scalable Reinforcement Learning Policies For Multi-agent Control (2020)10.21
• Using Reinforcement Learning To Herd A Robotic Swarm To A Target Distribution (2020)4.52
• Descent-guided Policy Gradient For Scalable Cooperative Multi-agent Learning (2026)0.00
• Asynchronous, Option-based Multi-agent Policy Gradient: A Conditional Reasoning Approach (2022)0.00
• Multi-agent Cooperation Through Learning-aware Policy Gradients (2024)0.00
• Policy Search By Target Distribution Learning For Continuous Control (2019)3.58