PHENOMENA AND PROCESSES Mathematical Concepts [G17] Mathematical Concepts Algorithms [G17.035] Algorithms Artificial Intelligence [G17.035.250] Artificial Intelligence Machine Learning [G17.035.250.500] Machine Learning Deep Learning [G17.035.250.500.250] Deep Learning Dimensionality Reduction [G17.035.250.500.375] Dimensionality Reduction Ensemble Learning [G17.035.250.500.438] Ensemble Learning Federated Learning [G17.035.250.500.469] Federated Learning Reinforcement Machine Learning [G17.035.250.500.485] Reinforcement Machine Learning Representation Machine Learning [G17.035.250.500.493] Representation Machine Learning Supervised Machine Learning [G17.035.250.500.500] Supervised Machine Learning Transfer Machine Learning [G17.035.250.500.625] Transfer Machine Learning Unsupervised Machine Learning [G17.035.250.500.750] Unsupervised Machine Learning INFORMATION SCIENCE Information Science [L01] Information Science Computing Methodologies [L01.224] Computing Methodologies Algorithms [L01.224.050] Algorithms Artificial Intelligence [L01.224.050.375] Artificial Intelligence Machine Learning [L01.224.050.375.530] Machine Learning Deep Learning [L01.224.050.375.530.250] Deep Learning Dimensionality Reduction [L01.224.050.375.530.375] Dimensionality Reduction Ensemble Learning [L01.224.050.375.530.438] Ensemble Learning Federated Learning [L01.224.050.375.530.469] Federated Learning Reinforcement Machine Learning [L01.224.050.375.530.485] Reinforcement Machine Learning Representation Machine Learning [L01.224.050.375.530.493] Representation Machine Learning Supervised Machine Learning [L01.224.050.375.530.500] Supervised Machine Learning Transfer Machine Learning [L01.224.050.375.530.625] Transfer Machine Learning Unsupervised Machine Learning [L01.224.050.375.530.750] Unsupervised Machine Learning

Reinforcement Machine Learning - Preferred

Concept UI	M000766619
Scope note	A machine learning training method in which an agent in an uncertain environment is rewarded for optimal behaviors and punished for undesired behaviors, allowing the agent to learn from trial-and-error.
Preferred term	Reinforcement Machine Learning
Entry term(s)	Machine Learning, Reinforcement Machine Reinforcement Learning Machine Reinforcement Learnings Reinforcement Learning, Machine Reinforcement Machine Learnings

Deep Reinforcement Learning - Narrower

Concept UI	M000767424
Preferred term	Deep Reinforcement Learning
Entry term(s)	Deep Reinforcement Learnings Reinforcement Learning, Deep