Salīdzināt metodes

	Multimodālā pastiprināšanas mācīšanās	Pārneses mācīšanās ar pastiprinājuma mācīšanos
Nozare	Dziļā mācīšanās	Dziļā mācīšanās
Saime	Machine learning	Machine learning
Izcelsmes gads	2015–2022	2009 (survey); concept from early 2000s
Autors	Multiple contributors (DeepMind, OpenAI, Google Brain, 2010s–2020s)	Taylor, M. E. & Stone, P.
Tips	Multimodal deep RL agent	Transfer learning paradigm for sequential decision-making
Pirmavots	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.	Taylor, M. E., & Stone, P. (2009). Transfer Learning for Reinforcement Learning Domains: A Survey. Journal of Machine Learning Research, 10, 1633–1685.
Citi nosaukumi	Multimodal RL, Multi-Sensory Reinforcement Learning, Vision-Language RL, Multi-Input RL	Transfer RL, TL for RL, cross-task reinforcement learning, inductive transfer in RL
Saistītās	6	4
Kopsavilkums	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.	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.