CoDreamer: Communication-Based Decentralised World Models
Sample efficiency is a critical challenge in reinforcement learning. Model-based RL has emerged as a solution, but its application has largely been confined to single-agent scenarios. In this work, we introduce CoDreamer, an extension of the Dreamer algorithm for multi-agent environments. CoDreamer leverages Graph Neural Networks for a two-level communication system to tackle challenges such as partial observability and inter-agent cooperation. Communication is separately utilised within the learned world models and within the learned policies of each agent to enhance modelling and task-solving. We show that CoDreamer offers greater expressive power than a naive application of Dreamer, and we demonstrate its superiority over baseline methods across various multi-agent environments.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
Decentralised Federated Learning over Temporal Networks: The Role of Heterogeneities
Decentralised federated learning, based on peer-to-peer communication, is increasingly proposed for on-device training of machine learning models, promising a privacy-preserving, communication-efficient training process …
Federated LearningDecentralised Multi-Demic Evolutionary Approach to the Dynamic Multi-Agent Travelling Salesman Problem
The Travelling Salesman and its variations are some of the most well known NP hard optimisation problems. This paper looks to use both centralised and decentralised implementations of Evolutionary Algorithms (EA) to solv…
Evolutionary AlgorithmsDecentralised Variational Inference Frameworks for Multi-object Tracking on Sensor Networks: Additional Notes
This paper tackles the challenge of multi-sensor multi-object tracking by proposing various decentralised Variational Inference (VI) schemes that match the tracking performance of centralised sensor fusion with only loca…
Multi-Object TrackingObjectObject TrackingSensor Fusion+1Multiagent Model-based Credit Assignment for Continuous Control
Deep reinforcement learning (RL) has recently shown great promise in robotic continuous control tasks. Nevertheless, prior research in this vein center around the centralized learning setting that largely relies on the c…
continuous-controlContinuous ControlDeep Reinforcement Learningmodel+4QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
In many real-world settings, a team of agents must coordinate their behaviour while acting in a decentralised way. At the same time, it is often possible to train the agents in a centralised fashion in a simulated or lab…
Multi-agent Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)+3