Multi-Agent Decentralized Belief Propagation on Graphs
- URL: http://arxiv.org/abs/2011.04501v2
- Date: Tue, 10 Nov 2020 02:25:35 GMT
- Title: Multi-Agent Decentralized Belief Propagation on Graphs
- Authors: Yitao Chen and Deepanshu Vasal
- Abstract summary: We consider the problem of interactive partially observable Markov decision processes (I-POMDPs)
We propose a decentralized belief propagation algorithm for the problem.
Our work appears to be the first study of decentralized belief propagation algorithm for networked multi-agent I-POMDPs.
- Score: 0.0
- License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
- Abstract: We consider the problem of interactive partially observable Markov decision
processes (I-POMDPs), where the agents are located at the nodes of a
communication network. Specifically, we assume a certain message type for all
messages. Moreover, each agent makes individual decisions based on the
interactive belief states, the information observed locally and the messages
received from its neighbors over the network. Within this setting, the
collective goal of the agents is to maximize the globally averaged return over
the network through exchanging information with their neighbors. We propose a
decentralized belief propagation algorithm for the problem, and prove the
convergence of our algorithm. Finally we show multiple applications of our
framework. Our work appears to be the first study of decentralized belief
propagation algorithm for networked multi-agent I-POMDPs.
Related papers
- Scalable spectral representations for network multiagent control [53.631272539560435]
A popular model for multi-agent control, Network Markov Decision Processes (MDPs) pose a significant challenge to efficient learning.
We first derive scalable spectral local representations for network MDPs, which induces a network linear subspace for the local $Q$-function of each agent.
We design a scalable algorithmic framework for continuous state-action network MDPs, and provide end-to-end guarantees for the convergence of our algorithm.
arXiv Detail & Related papers (2024-10-22T17:45:45Z) - Networked Communication for Mean-Field Games with Function Approximation and Empirical Mean-Field Estimation [59.01527054553122]
Decentralised agents can learn equilibria in Mean-Field Games from a single, non-episodic run of the empirical system.
We introduce function approximation to the existing setting, drawing on the Munchausen Online Mirror Descent method.
We additionally provide new algorithms that allow agents to estimate the global empirical distribution based on a local neighbourhood.
arXiv Detail & Related papers (2024-08-21T13:32:46Z) - Decentralized Monte Carlo Tree Search for Partially Observable
Multi-agent Pathfinding [49.730902939565986]
Multi-Agent Pathfinding problem involves finding a set of conflict-free paths for a group of agents confined to a graph.
In this study, we focus on the decentralized MAPF setting, where the agents may observe the other agents only locally.
We propose a decentralized multi-agent Monte Carlo Tree Search (MCTS) method for MAPF tasks.
arXiv Detail & Related papers (2023-12-26T06:57:22Z) - Continuous-Time Distributed Dynamic Programming for Networked Multi-Agent Markov Decision Processes [7.464789724562025]
This paper investigates continuous-time distributed dynamic programming (DP) algorithms for networked multi-agent Markov decision problems (MAMDPs)
In our study, we adopt a distributed multi-agent framework where individual agents have access only to their own rewards, lacking insights into the rewards of other agents.
arXiv Detail & Related papers (2023-07-31T14:25:20Z) - Distributed Online Rollout for Multivehicle Routing in Unmapped
Environments [0.8437187555622164]
We present a fully distributed, online, and scalable reinforcement learning algorithm for the well-known multivehicle routing problem.
Agents self-organize into local clusters and independently apply a multiagent rollout scheme locally to each cluster.
Our algorithm achieves approximately a factor of two cost improvement over the base policy for a range of radii bounded from below and above by two and three times the critical sensing radius, respectively.
arXiv Detail & Related papers (2023-05-24T22:06:44Z) - Policy Evaluation in Decentralized POMDPs with Belief Sharing [39.550233049869036]
We consider a cooperative policy evaluation task in which agents are not assumed to observe the environment state directly.
We propose a fully decentralized belief forming strategy that relies on individual updates and on localized interactions over a communication network.
arXiv Detail & Related papers (2023-02-08T15:54:15Z) - Competing Adaptive Networks [56.56653763124104]
We develop an algorithm for decentralized competition among teams of adaptive agents.
We present an application in the decentralized training of generative adversarial neural networks.
arXiv Detail & Related papers (2021-03-29T14:42:15Z) - Learning Connectivity for Data Distribution in Robot Teams [96.39864514115136]
We propose a task-agnostic, decentralized, low-latency method for data distribution in ad-hoc networks using Graph Neural Networks (GNN)
Our approach enables multi-agent algorithms based on global state information to function by ensuring it is available at each robot.
We train the distributed GNN communication policies via reinforcement learning using the average Age of Information as the reward function and show that it improves training stability compared to task-specific reward functions.
arXiv Detail & Related papers (2021-03-08T21:48:55Z) - HAMMER: Multi-Level Coordination of Reinforcement Learning Agents via
Learned Messaging [14.960795846548029]
Cooperative multi-agent reinforcement learning (MARL) has achieved significant results, most notably by leveraging the representation learning abilities of deep neural networks.
This paper considers the case where there is a single, powerful, central agent that can observe the entire observation space, and there are multiple, low powered, local agents that can only receive local observations and cannot communicate with each other.
The job of the central agent is to learn what message to send to different local agents, based on the global observations, but by determining what additional information an individual agent should receive so that it can make a better decision.
arXiv Detail & Related papers (2021-01-18T19:00:12Z) - Detecting Communities in Heterogeneous Multi-Relational Networks:A
Message Passing based Approach [89.19237792558687]
Community is a common characteristic of networks including social networks, biological networks, computer and information networks.
We propose an efficient message passing based algorithm to simultaneously detect communities for all homogeneous networks.
arXiv Detail & Related papers (2020-04-06T17:36:24Z) - A Visual Communication Map for Multi-Agent Deep Reinforcement Learning [7.003240657279981]
Multi-agent learning poses significant challenges in the effort to allocate a concealed communication medium.
Recent studies typically combine a specialized neural network with reinforcement learning to enable communication between agents.
This paper proposes a more scalable approach that not only deals with a great number of agents but also enables collaboration between dissimilar functional agents.
arXiv Detail & Related papers (2020-02-27T02:38:21Z)
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.