Comparer des méthodes

	Apprentissage par transfert avec apprentissage par renforcement	Apprentissage par transfert avec réseau neuronal convolutif
Domaine	Apprentissage profond	Apprentissage profond
Famille	Machine learning	Machine learning
Année d'origine	2009 (survey); concept from early 2000s	2010–2014
Auteur d'origine	Taylor, M. E. & Stone, P.	Pan, S. J. & Yang, Q. (transfer learning framework); popularized for CNNs by Yosinski et al. and Razavian et al.
Type	Transfer learning paradigm for sequential decision-making	Transfer learning applied to convolutional neural networks
Source fondatrice	Taylor, M. E., & Stone, P. (2009). Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research, 10, 1633–1685.	Pan, S. J., & Yang, Q. (2010). A Survey on Transfer Learning. IEEE Transactions on Knowledge and Data Engineering, 22(10), 1345–1359.
Alias	Transfer RL, TL for RL, cross-task reinforcement learning, inductive transfer in RL	TL-CNN, pretrained CNN, CNN fine-tuning, feature-extracting CNN
Apparentées	4	4
Résumé	Transfer Learning with Reinforcement Learning (Transfer RL) is a training paradigm in which knowledge acquired by an agent in one or more source tasks — encoded as policy weights, value functions, or learned representations — is reused to accelerate or improve learning in a related but different target task. It directly addresses the sample-inefficiency that plagues reinforcement learning from scratch in complex or expensive environments.	Transfer Learning with CNN reuses a convolutional neural network that has already been trained on a large dataset — most commonly ImageNet — and adapts its learned feature detectors to a new, often smaller target dataset. This lets researchers achieve strong image-recognition performance without the massive compute and data resources required to train a CNN from scratch.