a type of machine learning where an agent learns to make decisions by performing actions and receiving feedback
вид машинного обучения, при котором агент учится принимать решения, выполняя действия и получая обратную связь (vid mashinnogo obucheniya, pri kotorom agent uchitsya prinimat' resheniya, vypolnyaya deystviya i poluchaya obratnuyu svyaz')
"In reinforcement learning, the model improves over time as it learns from trial and error."
"В reinforcement learning модель улучшает себя со временем, обучаясь на пробах и ошибках." (V **reinforcement learning** model' uluchshaet sebya so vremenem, obuchayas' na probakh i oshibkakh.)
safe and unharmed after a difficult situation
to allow others to live as they choose without interference
when advice or complaints are ignored
someone who is honest and morally upright
to become famous or well known for something
to continue doing something despite challenges
