CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation

• URL: http://arxiv.org/abs/2411.04679v1
• Date: Thu, 07 Nov 2024 13:08:04 GMT
• Title: CaPo: Cooperative Plan Optimization for Efficient Embodied Multi-Agent Cooperation
• Authors: Jie Liu, Pan Zhou, Yingjun Du, Ah-Hwee Tan, Cees G. M. Snoek, Jan-Jakob Sonke, Efstratios Gavves,
• Abstract summary: CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution. Experimental results on the ThreeDworld Multi-Agent Transport and Communicative Watch-And-Help tasks demonstrate that CaPo achieves much higher task completion rate and efficiency compared with state-of-the-arts.
• Score: 98.11670473661587
• License:
• Abstract: In this work, we address the cooperation problem among large language model (LLM) based embodied agents, where agents must cooperate to achieve a common goal. Previous methods often execute actions extemporaneously and incoherently, without long-term strategic and cooperative planning, leading to redundant steps, failures, and even serious repercussions in complex tasks like search-and-rescue missions where discussion and cooperative plan are crucial. To solve this issue, we propose Cooperative Plan Optimization (CaPo) to enhance the cooperation efficiency of LLM-based embodied agents. Inspired by human cooperation schemes, CaPo improves cooperation efficiency with two phases: 1) meta-plan generation, and 2) progress-adaptive meta-plan and execution. In the first phase, all agents analyze the task, discuss, and cooperatively create a meta-plan that decomposes the task into subtasks with detailed steps, ensuring a long-term strategic and coherent plan for efficient coordination. In the second phase, agents execute tasks according to the meta-plan and dynamically adjust it based on their latest progress (e.g., discovering a target object) through multi-turn discussions. This progress-based adaptation eliminates redundant actions, improving the overall cooperation efficiency of agents. Experimental results on the ThreeDworld Multi-Agent Transport and Communicative Watch-And-Help tasks demonstrate that CaPo achieves much higher task completion rate and efficiency compared with state-of-the-arts.

Related papers

• Cooperative Strategic Planning Enhances Reasoning Capabilities in Large Language Models [37.899581994741865]
  This paper proposes a novel cooperative multi-agent reasoning framework (CoPlanner) CoPlanner consists of two LLM agents: a planning agent and a reasoning agent. Our results demonstrate that the guidance from the planning agent and the effective cooperation between the agents contribute to the superior performance of CoPlanner.
  arXiv  Detail & Related papers  (2024-10-25T23:32:48Z)
• Towards Collaborative Intelligence: Propagating Intentions and Reasoning for Multi-Agent Coordination with Large Language Models [41.95288786980204]
  Current agent frameworks often suffer from dependencies on single-agent execution and lack robust inter- module communication. We present a framework for training large language models as collaborative agents to enable coordinated behaviors in cooperative MARL. A propagation network transforms broadcast intentions into teammate-specific communication messages, sharing relevant goals with designated teammates.
  arXiv  Detail & Related papers  (2024-07-17T13:14:00Z)
• CoAct: A Global-Local Hierarchy for Autonomous Agent Collaboration [87.51781348070914]
  Existing LLMs exhibit remarkable performance on various NLP tasks, but still struggle with complex real-world tasks. We propose the CoAct framework, which transfers the hierarchical planning and collaboration patterns in human society to LLM systems.
  arXiv  Detail & Related papers  (2024-06-19T09:23:53Z)
• Anticipate & Collab: Data-driven Task Anticipation and Knowledge-driven Planning for Human-robot Collaboration [13.631341660350028]
  An agent assisting humans in daily living activities can collaborate more effectively by anticipating upcoming tasks. Data-driven methods represent the state of the art in task anticipation, planning, and related problems, but these methods are resource-hungry and opaque. This paper describes DaTAPlan, our framework that significantly extends our prior work toward human-robot collaboration.
  arXiv  Detail & Related papers  (2024-04-04T16:52:48Z)
• Decentralized and Lifelong-Adaptive Multi-Agent Collaborative Learning [57.652899266553035]
  Decentralized and lifelong-adaptive multi-agent collaborative learning aims to enhance collaboration among multiple agents without a central server. We propose DeLAMA, a decentralized multi-agent lifelong collaborative learning algorithm with dynamic collaboration graphs.
  arXiv  Detail & Related papers  (2024-03-11T09:21:11Z)
• Learning Multi-Agent Intention-Aware Communication for Optimal Multi-Order Execution in Finance [96.73189436721465]
  We first present a multi-agent RL (MARL) method for multi-order execution considering practical constraints. We propose a learnable multi-round communication protocol, for the agents communicating the intended actions with each other. Experiments on the data from two real-world markets have illustrated superior performance with significantly better collaboration effectiveness.
  arXiv  Detail & Related papers  (2023-07-06T16:45:40Z)
• E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance [20.03014783858498]
  We introduce Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance(E-MAPP) E-MAPP is a novel framework that leverages parallel programs to guide multiple agents to efficiently accomplish goals that require planning over $10+$ stages. Results show that E-MAPP outperforms strong baselines in terms of the completion rate, time efficiency, and zero-shot generalization ability by a large margin.
  arXiv  Detail & Related papers  (2022-12-05T07:02:05Z)
• UneVEn: Universal Value Exploration for Multi-Agent Reinforcement Learning [53.73686229912562]
  We propose a novel MARL approach called Universal Value Exploration (UneVEn) UneVEn learns a set of related tasks simultaneously with a linear decomposition of universal successor features. Empirical results on a set of exploration games, challenging cooperative predator-prey tasks requiring significant coordination among agents, and StarCraft II micromanagement benchmarks show that UneVEn can solve tasks where other state-of-the-art MARL methods fail.
  arXiv  Detail & Related papers  (2020-10-06T19:08:47Z)
• A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks [111.34055449929487]
  We introduce the novel task FurnMove in which agents work together to move a piece of furniture through a living room to a goal. Unlike existing tasks, FurnMove requires agents to coordinate at every timestep. We identify two challenges when training agents to complete FurnMove: existing decentralized action sampling procedures do not permit expressive joint action policies. Using SYNC-policies and CORDIAL, our agents achieve a 58% completion rate on FurnMove, an impressive absolute gain of 25 percentage points over competitive decentralized baselines.
  arXiv  Detail & Related papers  (2020-07-09T17:59:57Z)
• Developing cooperative policies for multi-stage tasks [0.0]
  This paper proposes the Cooperative Soft Actor Critic (CSAC) method of enabling consecutive reinforcement learning agents to cooperatively solve a long time horizon multi-stage task. CSAC achieved a success rate of at least 20% higher than the uncooperative policies, and converged on a solution at least 4 times faster than the single agent.
  arXiv  Detail & Related papers  (2020-07-01T03:32:14Z)

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.