Decision Making and Reinforcement Learning
Completed by Dragan Obradovic
September 5, 2024
47 hours (approximately)
Dragan Obradovic's account is verified. Coursera certifies their successful completion of Decision Making and Reinforcement Learning
What you will learn
Map between qualitative preferences and appropriate quantitative utilities.
Model non-associative and associative sequential decision problems with multi-armed bandit problems and Markov decision processes respectively
Implement dynamic programming algorithms to find optimal policies
Implement basic reinforcement learning algorithms using Monte Carlo and temporal difference methods
Skills you will gain
- Category: Statistical Methods
- Category: Analysis
- Category: Machine Learning
- Category: Machine Learning Methods
- Category: Deep Learning
- Category: Decision Intelligence
- Category: Artificial Intelligence and Machine Learning (AI/ML)
- Category: Reinforcement Learning
- Category: Machine Learning Algorithms
- Category: Algorithms
- Category: Markov Model
