CoDreamer: Communication-Based Decentralised World Models
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911926695493632 |
|---|---|
| author | Toledo, Edan Prorok, Amanda |
| author_facet | Toledo, Edan Prorok, Amanda |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_13600 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | CoDreamer: Communication-Based Decentralised World Models Toledo, Edan Prorok, Amanda Artificial Intelligence 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. |
| title | CoDreamer: Communication-Based Decentralised World Models |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2406.13600 |