Graph Neural Networks with Model-based Reinforcement Learning for Multi-agent Systems

• URL: http://arxiv.org/abs/2407.09249v2
• Date: Sun, 29 Sep 2024 13:18:51 GMT
• Title: Graph Neural Networks with Model-based Reinforcement Learning for Multi-agent Systems
• Authors: Hanxiao Chen,
• Abstract summary: Multi-agent systems (MAS) constitute a significant role in exploring machine intelligence and advanced applications. We originally propose "GNN for MBRL" model, which utilizes a state-spaced Graph Neural Networks with Model-based Reinforcement Learning to address specific MAS missions. In detail, we firstly used GNN model to predict future states and trajectories of multiple agents, then applied the Cross-Entropy Method (CEM) optimized Model Predictive Control to assist the ego-agent planning actions and successfully accomplish certain MAS tasks.
• Score: 11.893324664457548
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent systems (MAS) constitute a significant role in exploring machine intelligence and advanced applications. In order to deeply investigate complicated interactions within MAS scenarios, we originally propose "GNN for MBRL" model, which utilizes a state-spaced Graph Neural Networks with Model-based Reinforcement Learning to address specific MAS missions (e.g., Billiard-Avoidance, Autonomous Driving Cars). In detail, we firstly used GNN model to predict future states and trajectories of multiple agents, then applied the Cross-Entropy Method (CEM) optimized Model Predictive Control to assist the ego-agent planning actions and successfully accomplish certain MAS tasks.

Related papers

• Rapid and Automated Alloy Design with Graph Neural Network-Powered LLM-Driven Multi-Agent Systems [0.0]
  A multi-agent AI model is used to automate the discovery of new metallic alloys. We focus on the NbMoTa family of body-centered cubic (bcc) alloys, modeled using an ML-based interatomic potential. By synergizing the predictive power of GNNs with the dynamic collaboration of LLM-based agents, the system autonomously navigates vast alloy design spaces.
  arXiv  Detail & Related papers  (2024-10-17T17:06:26Z)
• An Interactive Agent Foundation Model [49.77861810045509]
  We propose an Interactive Agent Foundation Model that uses a novel multi-task agent training paradigm for training AI agents. Our training paradigm unifies diverse pre-training strategies, including visual masked auto-encoders, language modeling, and next-action prediction. We demonstrate the performance of our framework across three separate domains -- Robotics, Gaming AI, and Healthcare.
  arXiv  Detail & Related papers  (2024-02-08T18:58:02Z)
• Learning Control Admissibility Models with Graph Neural Networks for Multi-Agent Navigation [9.05607520128194]
  Control admissibility models (CAMs) can be easily composed and used for online inference for an arbitrary number of agents. We show that the CAM models can be trained in environments with only a few agents and be easily composed for deployment in dense environments with hundreds of agents, achieving better performance than state-of-the-art methods.
  arXiv  Detail & Related papers  (2022-10-17T19:20:58Z)
• Multitask Adaptation by Retrospective Exploration with Learned World Models [77.34726150561087]
  We propose a meta-learned addressing model called RAMa that provides training samples for the MBRL agent taken from task-agnostic storage. The model is trained to maximize the expected agent's performance by selecting promising trajectories solving prior tasks from the storage.
  arXiv  Detail & Related papers  (2021-10-25T20:02:57Z)
• Efficient Model-Based Multi-Agent Mean-Field Reinforcement Learning [89.31889875864599]
  We propose an efficient model-based reinforcement learning algorithm for learning in multi-agent systems. Our main theoretical contributions are the first general regret bounds for model-based reinforcement learning for MFC. We provide a practical parametrization of the core optimization problem.
  arXiv  Detail & Related papers  (2021-07-08T18:01:02Z)
• Graph Neural Networks for Decentralized Multi-Robot Submodular Action Selection [101.38634057635373]
  We focus on applications where robots are required to jointly select actions to maximize team submodular objectives. We propose a general-purpose learning architecture towards submodular at scale, with decentralized communications. We demonstrate the performance of our GNN-based learning approach in a scenario of active target coverage with large networks of robots.
  arXiv  Detail & Related papers  (2021-05-18T15:32:07Z)
• A Driving Behavior Recognition Model with Bi-LSTM and Multi-Scale CNN [59.57221522897815]
  We propose a neural network model based on trajectories information for driving behavior recognition. We evaluate the proposed model on the public BLVD dataset, achieving a satisfying performance.
  arXiv  Detail & Related papers  (2021-03-01T06:47:29Z)
• Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning [12.988435681305281]
  Graph Neural Networks (GNNs) have become popular due to their ability to learn communication policies in decentralized multi-agent systems. We extend our previous work that utilizes GNNs in multi-agent path planning by incorporating a novel mechanism to allow for message-dependent attention. Our Message-Aware Graph Attention neTwork (MAGAT) is based on a key-query-like mechanism that determines the relative importance of features in the messages received from various neighboring robots.
  arXiv  Detail & Related papers  (2020-11-26T10:37:13Z)
• Optimizing Large-Scale Fleet Management on a Road Network using Multi-Agent Deep Reinforcement Learning with Graph Neural Network [0.8702432681310401]
  We propose a novel approach to optimize fleet management by combining multi-agent reinforcement learning with graph neural network. We design a realistic simulator that emulates the empirical taxi call data, and confirm the effectiveness of the proposed model under various conditions.
  arXiv  Detail & Related papers  (2020-11-12T03:01:37Z)
• Trajectory-wise Multiple Choice Learning for Dynamics Generalization in Reinforcement Learning [137.39196753245105]
  We present a new model-based reinforcement learning algorithm that learns a multi-headed dynamics model for dynamics generalization. We incorporate context learning, which encodes dynamics-specific information from past experiences into the context latent vector. Our method exhibits superior zero-shot generalization performance across a variety of control tasks, compared to state-of-the-art RL methods.
  arXiv  Detail & Related papers  (2020-10-26T03:20:42Z)
• MagNet: Discovering Multi-agent Interaction Dynamics using Neural Network [11.285833408524708]
  MagNet is a neural network-based multi-agent interaction model. It is trained to discover the core dynamics of a multi-agent system from observations. It is tuned on-line to learn agent-specific parameters to ensure accurate prediction.
  arXiv  Detail & Related papers  (2020-01-24T13:41:01Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.