Learning Flexible Heterogeneous Coordination with Capability-Aware Shared Hypernetworks
- URL: http://arxiv.org/abs/2501.06058v2
- Date: Tue, 18 Feb 2025 09:23:35 GMT
- Title: Learning Flexible Heterogeneous Coordination with Capability-Aware Shared Hypernetworks
- Authors: Kevin Fu, Pierce Howell, Shalin Jain, Harish Ravichandar,
- Abstract summary: We present Capability-Aware Shared Hypernetworks (CASH), a novel architecture for heterogeneous multi-agent coordination.
CASH generates sufficient diversity while maintaining sample-efficiency via soft parameter-sharing hypernetworks.
We present experiments across two heterogeneous coordination tasks and three standard learning paradigms.
- Score: 2.681242476043447
- License:
- Abstract: Cooperative heterogeneous multi-agent tasks require agents to effectively coordinate their behaviors while accounting for their relative capabilities. Learning-based solutions to this challenge span between two extremes: i) shared-parameter methods, which encode diverse behaviors within a single architecture by assigning an ID to each agent, and are sample-efficient but result in limited behavioral diversity; ii) independent methods, which learn a separate policy for each agent, and show greater behavioral diversity but lack sample-efficiency. Prior work has also explored selective parameter-sharing, allowing for a compromise between diversity and efficiency. None of these approaches, however, effectively generalize to unseen agents or teams. We present Capability-Aware Shared Hypernetworks (CASH), a novel architecture for heterogeneous multi-agent coordination that generates sufficient diversity while maintaining sample-efficiency via soft parameter-sharing hypernetworks. Intuitively, CASH allows the team to learn common strategies using a shared encoder, which are then adapted according to the team's individual and collective capabilities with a hypernetwork, allowing for zero-shot generalization to unseen teams and agents. We present experiments across two heterogeneous coordination tasks and three standard learning paradigms (imitation learning, on- and off-policy reinforcement learning). CASH is able to outperform baseline architectures in success rate and sample efficiency when evaluated on unseen teams and agents despite using less than half of the learnable parameters.
Related papers
- HyperMARL: Adaptive Hypernetworks for Multi-Agent RL [10.00022425344723]
HyperMARL is a parameter sharing approach that uses hypernetworks to generate agent-specific parameters without altering the learning objective.
It consistently performs competitively with fully shared, non- parameter-sharing, and diversity-promoting baselines.
These findings establish hypernetworks as a versatile approach for MARL across diverse environments.
arXiv Detail & Related papers (2024-12-05T15:09:51Z) - 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) - Adaptive parameter sharing for multi-agent reinforcement learning [16.861543418593044]
We propose a novel parameter sharing method inspired by research pertaining to the brain in biology.
It maps each type of agent to different regions within a shared network based on their identity, resulting in distinctworks.
Our method can increase the diversity of strategies among different agents without additional training parameters.
arXiv Detail & Related papers (2023-12-14T15:00:32Z) - 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) - CoMIX: A Multi-agent Reinforcement Learning Training Architecture for Efficient Decentralized Coordination and Independent Decision-Making [2.4555276449137042]
Robust coordination skills enable agents to operate cohesively in shared environments, together towards a common goal and, ideally, individually without hindering each other's progress.
This paper presents Coordinated QMIX, a novel training framework for decentralized agents that enables emergent coordination through flexible policies, allowing at the same time independent decision-making at individual level.
arXiv Detail & Related papers (2023-08-21T13:45:44Z) - Learning Heterogeneous Agent Cooperation via Multiagent League Training [6.801749815385998]
This work proposes a general-purpose reinforcement learning algorithm named Heterogeneous League Training (HLT) to address heterogeneous multiagent problems.
HLT keeps track of a pool of policies that agents have explored during training, gathering a league of heterogeneous policies to facilitate future policy optimization.
A hyper-network is introduced to increase the diversity of agent behaviors when collaborating with teammates having different levels of cooperation skills.
arXiv Detail & Related papers (2022-11-13T13:57:15Z) - Multi-agent Deep Covering Skill Discovery [50.812414209206054]
We propose Multi-agent Deep Covering Option Discovery, which constructs the multi-agent options through minimizing the expected cover time of the multiple agents' joint state space.
Also, we propose a novel framework to adopt the multi-agent options in the MARL process.
We show that the proposed algorithm can effectively capture the agent interactions with the attention mechanism, successfully identify multi-agent options, and significantly outperforms prior works using single-agent options or no options.
arXiv Detail & Related papers (2022-10-07T00:40:59Z) - Policy Diagnosis via Measuring Role Diversity in Cooperative Multi-agent
RL [107.58821842920393]
We quantify the agent's behavior difference and build its relationship with the policy performance via bf Role Diversity
We find that the error bound in MARL can be decomposed into three parts that have a strong relation to the role diversity.
The decomposed factors can significantly impact policy optimization on three popular directions.
arXiv Detail & Related papers (2022-06-01T04:58:52Z) - LDSA: Learning Dynamic Subtask Assignment in Cooperative Multi-Agent
Reinforcement Learning [122.47938710284784]
We propose a novel framework for learning dynamic subtask assignment (LDSA) in cooperative MARL.
To reasonably assign agents to different subtasks, we propose an ability-based subtask selection strategy.
We show that LDSA learns reasonable and effective subtask assignment for better collaboration.
arXiv Detail & Related papers (2022-05-05T10:46:16Z) - Multi-Agent Imitation Learning with Copulas [102.27052968901894]
Multi-agent imitation learning aims to train multiple agents to perform tasks from demonstrations by learning a mapping between observations and actions.
In this paper, we propose to use copula, a powerful statistical tool for capturing dependence among random variables, to explicitly model the correlation and coordination in multi-agent systems.
Our proposed model is able to separately learn marginals that capture the local behavioral patterns of each individual agent, as well as a copula function that solely and fully captures the dependence structure among agents.
arXiv Detail & Related papers (2021-07-10T03:49:41Z) - Celebrating Diversity in Shared Multi-Agent Reinforcement Learning [20.901606233349177]
Deep multi-agent reinforcement learning has shown the promise to solve complex cooperative tasks.
In this paper, we aim to introduce diversity in both optimization and representation of shared multi-agent reinforcement learning.
Our method achieves state-of-the-art performance on Google Research Football and super hard StarCraft II micromanagement tasks.
arXiv Detail & Related papers (2021-06-04T00:55:03Z)
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.