Concept
Multi-armed bandit
Related lectures (28)
Learning Agents: Exploration-Exploitation Tradeoff
Explores the exploration-exploitation tradeoff in learning unknown effects of actions using multi-armed bandits and Q-learning.
Chemical Reaction Optimization: Multi-Task Learning
Explores multi-task learning for accelerated chemical reaction optimization, showcasing challenges, automated workflows, and optimization algorithms.
Reinforcement Learning: Bandit Problems
Covers the convergence in expectation for the Q value in reinforcement learning.
Reinforcement Learning: BackUp Diagrams
Introduces the BackUp diagram as a key graphic representation in reinforcement learning.
Reinforcement Learning: One-step Horizon (Bandit Problems)
Covers Bandit Problems in Reinforcement Learning, focusing on one-step horizon games and Q-values.
Deep Learning Agents: Reinforcement Learning
Explores Deep Learning Agents in Reinforcement Learning, emphasizing neural network approximations and challenges in training multiagent systems.
Contextual Bandits: Simplifying Strategy for Content Selection
Introduces contextual bandits for content selection based on different contexts.
Generalization Error
Discusses mutual information, data processing inequality, and properties related to leakage in discrete systems.
Asset Pricing: Fundamental Theorems
Covers the fundamental theorems of asset pricing, including EMM, self-financing strategies, risk-neutral pricing, and completeness of markets.
Introduction: Foundations of Data Science
Covers distribution estimation, property testing, and multi-arm bandits in data science.