Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication

• URL: http://arxiv.org/abs/2004.00470v2
• Date: Tue, 29 Dec 2020 00:57:59 GMT
• Title: Counterfactual Multi-Agent Reinforcement Learning with Graph Convolution Communication
• Authors: Jianyu Su, Stephen Adams, and Peter A. Beling
• Abstract summary: We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility. We propose that multi-agent systems must have the ability to communicate and understand the inter-plays between agents. We develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent.
• Score: 5.5438676149999075
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: We consider a fully cooperative multi-agent system where agents cooperate to maximize a system's utility in a partial-observable environment. We propose that multi-agent systems must have the ability to (1) communicate and understand the inter-plays between agents and (2) correctly distribute rewards based on an individual agent's contribution. In contrast, most work in this setting considers only one of the above abilities. In this study, we develop an architecture that allows for communication among agents and tailors the system's reward for each individual agent. Our architecture represents agent communication through graph convolution and applies an existing credit assignment structure, counterfactual multi-agent policy gradient (COMA), to assist agents to learn communication by back-propagation. The flexibility of the graph structure enables our method to be applicable to a variety of multi-agent systems, e.g. dynamic systems that consist of varying numbers of agents and static systems with a fixed number of agents. We evaluate our method on a range of tasks, demonstrating the advantage of marrying communication with credit assignment. In the experiments, our proposed method yields better performance than the state-of-art methods, including COMA. Moreover, we show that the communication strategies offers us insights and interpretability of the system's cooperative policies.

Related papers

• Communication Learning in Multi-Agent Systems from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. We introduce a temporal gating mechanism for each agent, enabling dynamic decisions on whether to receive shared information at a given time.
  arXiv  Detail & Related papers  (2024-11-01T05:56:51Z)
• Learning Multi-Agent Communication from Graph Modeling Perspective [62.13508281188895]
  We introduce a novel approach wherein we conceptualize the communication architecture among agents as a learnable graph. Our proposed approach, CommFormer, efficiently optimize the communication graph and concurrently refines architectural parameters through gradient descent in an end-to-end manner.
  arXiv  Detail & Related papers  (2024-05-14T12:40:25Z)
• AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors [93.38830440346783]
  We propose a multi-agent framework framework that can collaboratively adjust its composition as a greater-than-the-sum-of-its-parts system. Our experiments demonstrate that framework framework can effectively deploy multi-agent groups that outperform a single agent. In view of these behaviors, we discuss some possible strategies to leverage positive ones and mitigate negative ones for improving the collaborative potential of multi-agent groups.
  arXiv  Detail & Related papers  (2023-08-21T16:47:11Z)
• Coordinating Policies Among Multiple Agents via an Intelligent Communication Channel [81.39444892747512]
  In Multi-Agent Reinforcement Learning (MARL), specialized channels are often introduced that allow agents to communicate directly with one another. We propose an alternative approach whereby agents communicate through an intelligent facilitator that learns to sift through and interpret signals provided by all agents to improve the agents' collective performance.
  arXiv  Detail & Related papers  (2022-05-21T14:11:33Z)
• Multi-agent Policy Optimization with Approximatively Synchronous Advantage Estimation [55.96893934962757]
  In multi-agent system, polices of different agents need to be evaluated jointly. In current methods, value functions or advantage functions use counter-factual joint actions which are evaluated asynchronously. In this work, we propose the approximatively synchronous advantage estimation.
  arXiv  Detail & Related papers  (2020-12-07T07:29:19Z)
• The Emergence of Adversarial Communication in Multi-Agent Reinforcement Learning [6.18778092044887]
  Many real-world problems require the coordination of multiple autonomous agents. Recent work has shown the promise of Graph Neural Networks (GNNs) to learn explicit communication strategies that enable complex multi-agent coordination. We show how a single self-interested agent is capable of learning highly manipulative communication strategies that allows it to significantly outperform a cooperative team of agents.
  arXiv  Detail & Related papers  (2020-08-06T12:48:08Z)
• 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)
• Learning Multi-Agent Coordination through Connectivity-driven Communication [7.462336024223669]
  In artificial multi-agent systems, the ability to learn collaborative policies is predicated upon the agents' communication skills. We present a deep reinforcement learning approach, Connectivity Driven Communication (CDC) CDC is able to learn effective collaborative policies and can over-perform competing learning algorithms on cooperative navigation tasks.
  arXiv  Detail & Related papers  (2020-02-12T20:58:33Z)
• Multi-Agent Interactions Modeling with Correlated Policies [53.38338964628494]
  In this paper, we cast the multi-agent interactions modeling problem into a multi-agent imitation learning framework. We develop a Decentralized Adrial Imitation Learning algorithm with Correlated policies (CoDAIL) Various experiments demonstrate that CoDAIL can better regenerate complex interactions close to the demonstrators.
  arXiv  Detail & Related papers  (2020-01-04T17:31:53Z)

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.