-UCB for Action Selection in Multi Agent Navigation
نویسندگان
چکیده
In multi-robot systems, efficient navigation is challenging as agents need to adjust their paths to account for potential collisions with other agents and static obstacles. In this paper, we present an online machine learning approach, -UCB, which improves global efficiency in the motions of multiple agents by building on ORCA, an existing multiagent navigation algorithm, and on UCB, a widely used action selection technique. With -UCB, agents adapt their motions to their local conditions while achieving globally efficient motions. We validate our approach experimentally, in a variety of scenarios and with different numbers of agents. Results show that agents using -UCB exhibit more globally time efficient motions, when compared to just ORCA and to UCB.
منابع مشابه
ALAN: Adaptive Learning for Multi-Agent Navigation
In multi-agent navigation, agents need to move towards their goal locations while avoiding collisions with other agents and static obstacles, often without communication with each other. Existing methods compute motions that are optimal locally but do not account for the aggregated motions of all agents, producing inefficient global behavior especially when agents move in a crowded space. In th...
متن کاملModified Uni-Vector Field Navigation and Modular Q-learning for Soccer Robots
The robot soccer system is being used as a test bed to develop the next generation of field robots. In the multiagent system, action selection is important for the cooperation and coordination among agents. There are many techniques in choosing a proper action of the agent. As the environment is dynamic, reinforcement learning is more suitable than supervised learning. Reinforcement learning is...
متن کاملModular Q-learning based multi-agent cooperation for robot soccer
In a multi-agent system, action selection is important for the cooperation and coordination among agents. As the environment is dynamic and complex, modular Q-learning, which is one of the reinforcement learning schemes, is employed in assigning a proper action to an agent in the multi-agent system. The architecture of modular Q-learning consists of learning modules and a mediator module. The m...
متن کاملAnalyzing a Multi-Agent-System Decision Architecture Aiming to Model the Behavior of Virtual Humans
In this paper a novel approach on how to model the decision-making of virtual humans in the domain of multi-agent-systems is analyzed. The developed decision architecture embeds strategic behavior for intelligent humanoid agents (Hoogendoorn & Bovy 2004). The aim is to solve the action selection problem in the domain of naturalistic decision-making related to pedestrian movements. Embedding ind...
متن کاملCollaborative Spatial Reuse in Wireless Networks via Selfish Multi-Armed Bandits
Next-generation wireless deployments are characterized by being dense and uncoordinated, which often leads to inefficient use of resources and poor performance. To solve this, we envision the utilization of completely decentralized mechanisms that enhance Spatial Reuse (SR). In particular, we concentrate in Reinforcement Learning (RL), and more specifically, in Multi-Armed Bandits (MABs), to al...
متن کامل