Comparer des méthodes

	Apprentissage par renforcement multimodal	Réseau neuronal graphique multimodal
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2015–2022	2019–2020
Auteur d'origine	Multiple contributors (DeepMind, OpenAI, Google Brain, 2010s–2020s)	Kipf & Welling (GNN foundation); extended to multimodal settings by multiple research groups c. 2019–2020
Type	Multimodal deep RL agent	Graph-based deep learning with multimodal input fusion
Source fondatrice	Reed, S., Zolna, K., Parisotto, E., Colmenarejo, S. G., Novikov, A., Barth-Maron, G., ... & de Freitas, N. (2022). A Generalist Agent. Transactions on Machine Learning Research.	Kipf, T. N., & Welling, M. (2017). Semi-Supervised Classification with Graph Convolutional Networks. International Conference on Learning Representations (ICLR).
Alias	Multimodal RL, Multi-Sensory Reinforcement Learning, Vision-Language RL, Multi-Input RL	MM-GNN, Multimodal GNN, Multi-modal Graph Network, Cross-modal Graph Neural Network
Apparentées	6	6
Résumé	Multimodal Reinforcement Learning trains agents to make sequential decisions by perceiving and integrating multiple input modalities — such as raw pixels, language instructions, audio, and proprioceptive sensors — simultaneously. Rather than acting on a single data stream, the agent fuses heterogeneous signals into a unified state representation and learns a policy through environmental reward feedback.	A Multimodal Graph Neural Network (MM-GNN) combines data from multiple modalities — such as text, images, and structured features — into a unified graph structure and applies graph-based message passing to learn joint representations. It enables relational reasoning across heterogeneous data sources, going beyond what unimodal or simple concatenation approaches can capture.