SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
- URL: http://arxiv.org/abs/2501.13200v1
- Date: Wed, 22 Jan 2025 20:08:53 GMT
- Title: SRMT: Shared Memory for Multi-agent Lifelong Pathfinding
- Authors: Alsu Sagirova, Yuri Kuratov, Mikhail Burtsev,
- Abstract summary: Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems.
One of the principal challenges in MARL is the need for explicit prediction of the agents' behavior to achieve cooperation.
We propose the Shared Recurrent Memory Transformer (SRMT) which extends memory transformers to multi-agent settings by pooling and globally broadcasting individual working memories.
- Score: 4.192235624580332
- License:
- Abstract: Multi-agent reinforcement learning (MARL) demonstrates significant progress in solving cooperative and competitive multi-agent problems in various environments. One of the principal challenges in MARL is the need for explicit prediction of the agents' behavior to achieve cooperation. To resolve this issue, we propose the Shared Recurrent Memory Transformer (SRMT) which extends memory transformers to multi-agent settings by pooling and globally broadcasting individual working memories, enabling agents to exchange information implicitly and coordinate their actions. We evaluate SRMT on the Partially Observable Multi-Agent Pathfinding problem in a toy Bottleneck navigation task that requires agents to pass through a narrow corridor and on a POGEMA benchmark set of tasks. In the Bottleneck task, SRMT consistently outperforms a variety of reinforcement learning baselines, especially under sparse rewards, and generalizes effectively to longer corridors than those seen during training. On POGEMA maps, including Mazes, Random, and MovingAI, SRMT is competitive with recent MARL, hybrid, and planning-based algorithms. These results suggest that incorporating shared recurrent memory into the transformer-based architectures can enhance coordination in decentralized multi-agent systems. The source code for training and evaluation is available on GitHub: https://github.com/Aloriosa/srmt.
Related papers
- O-MAPL: Offline Multi-agent Preference Learning [5.4482836906033585]
Inferring reward functions from demonstrations is a key challenge in reinforcement learning (RL)
We introduce a novel end-to-end preference-based learning framework for cooperative MARL.
Our algorithm outperforms existing methods across various tasks.
arXiv Detail & Related papers (2025-01-31T08:08:20Z) - Improving Retrieval-Augmented Generation through Multi-Agent Reinforcement Learning [51.54046200512198]
Retrieval-augmented generation (RAG) is extensively utilized to incorporate external, current knowledge into large language models.
A standard RAG pipeline may comprise several components, such as query rewriting, document retrieval, document filtering, and answer generation.
To overcome these challenges, we propose treating the RAG pipeline as a multi-agent cooperative task, with each component regarded as an RL agent.
arXiv Detail & Related papers (2025-01-25T14:24:50Z) - PPS-QMIX: Periodically Parameter Sharing for Accelerating Convergence of
Multi-Agent Reinforcement Learning [20.746383793882984]
Training for multi-agent reinforcement learning(MARL) is a time-consuming process.
One drawback is that strategy of each agent in MARL is independent but actually in cooperation.
We propose three simple approaches called Average Sharing(A-PPS), Reward-Scalability Periodically and Partial Personalized Periodically.
arXiv Detail & Related papers (2024-03-05T03:59:01Z) - A Bayesian Framework of Deep Reinforcement Learning for Joint O-RAN/MEC
Orchestration [12.914011030970814]
Multi-access Edge Computing (MEC) can be implemented together with Open Radio Access Network (O-RAN) over commodity platforms to offer low-cost deployment.
In this paper, a joint O-RAN/MEC orchestration using a Bayesian deep reinforcement learning (RL)-based framework is proposed.
arXiv Detail & Related papers (2023-12-26T18:04:49Z) - Learning Reward Machines in Cooperative Multi-Agent Tasks [75.79805204646428]
This paper presents a novel approach to Multi-Agent Reinforcement Learning (MARL)
It combines cooperative task decomposition with the learning of reward machines (RMs) encoding the structure of the sub-tasks.
The proposed method helps deal with the non-Markovian nature of the rewards in partially observable environments.
arXiv Detail & Related papers (2023-03-24T15:12:28Z) - Learning From Good Trajectories in Offline Multi-Agent Reinforcement
Learning [98.07495732562654]
offline multi-agent reinforcement learning (MARL) aims to learn effective multi-agent policies from pre-collected datasets.
One agent learned by offline MARL often inherits this random policy, jeopardizing the performance of the entire team.
We propose a novel framework called Shared Individual Trajectories (SIT) to address this problem.
arXiv Detail & Related papers (2022-11-28T18:11:26Z) - RPM: Generalizable Behaviors for Multi-Agent Reinforcement Learning [90.43925357575543]
We propose ranked policy memory ( RPM) to collect diverse multi-agent trajectories for training MARL policies with good generalizability.
RPM enables MARL agents to interact with unseen agents in multi-agent generalization evaluation scenarios and complete given tasks, and it significantly boosts the performance up to 402% on average.
arXiv Detail & Related papers (2022-10-18T07:32:43Z) - Multi-Agent Reinforcement Learning is a Sequence Modeling Problem [33.679936867612525]
We introduce a novel architecture named Multi-Agent Transformer (MAT)
MAT casts cooperative multi-agent reinforcement learning (MARL) into SM problems.
Central to MAT is an encoder-decoder architecture which transforms the joint policy search problem into a sequential decision making process.
arXiv Detail & Related papers (2022-05-30T09:39:45Z) - MACRPO: Multi-Agent Cooperative Recurrent Policy Optimization [17.825845543579195]
We propose a new multi-agent actor-critic method called textitMulti-Agent Cooperative Recurrent Proximal Policy Optimization (MACRPO)
We use a recurrent layer in critic's network architecture and propose a new framework to use a meta-trajectory to train the recurrent layer.
We evaluate our algorithm on three challenging multi-agent environments with continuous and discrete action spaces.
arXiv Detail & Related papers (2021-09-02T12:43:35Z) - MALib: A Parallel Framework for Population-based Multi-agent
Reinforcement Learning [61.28547338576706]
Population-based multi-agent reinforcement learning (PB-MARL) refers to the series of methods nested with reinforcement learning (RL) algorithms.
We present MALib, a scalable and efficient computing framework for PB-MARL.
arXiv Detail & Related papers (2021-06-05T03:27:08Z) - 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)
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.