השוואת שיטות

	למידת חיזוק רב-לשונית	שיכוני משפטים רב-לשוניים
תחום	למידה עמוקה	למידה עמוקה
משפחה	Machine learning	Machine learning
שנת המקור	2010s (applied to multilingual NLP settings)	2019–2022
הוגה השיטה	Sutton, R. S. & Barto, A. G. (RL foundations); multilingual extensions emerged from the NLP/RL community in the 2010s	Reimers, N. & Gurevych, I.; Feng, F. et al. (Google)
סוג	Reinforcement learning applied to multilingual environments	Cross-lingual representation learning
מקור מכונן	Sutton, R. S., & Barto, A. G. (1998). Reinforcement Learning: An Introduction. MIT Press. ISBN: 978-0262193986	Reimers, N. & Gurevych, I. (2020). Making Monolingual Sentence Embeddings Multilingual using Knowledge Distillation. Proceedings of EMNLP 2020, 4512–4525.
כינויים	Cross-Lingual RL, Multilingual RL, Multilingual Policy Learning, Cross-Lingual Reinforcement Learning	multilingual sentence representations, cross-lingual sentence embeddings, mSE, multilingual semantic embeddings
קשורות	5	5
תקציר	Multilingual Reinforcement Learning applies the RL paradigm — an agent learning by interaction and reward — to environments that involve multiple languages. The agent must interpret multilingual observations, follow cross-lingual instructions, or generalize policies trained in one language to new target languages, making it applicable to cross-lingual dialogue, multilingual game-playing agents, and language-grounded sequential decision tasks.	Multilingual sentence embeddings map sentences from many languages into a single shared vector space so that semantically equivalent sentences — regardless of language — land close together. Models such as LaBSE, multilingual Sentence-BERT, and mUSE have made it practical to compare, retrieve, and classify text across 50 to 100+ languages without translating anything first.