Policy evaluation in reinforcement learning, including limits of average reward objectives and alternatives that account for worst-case outcomes.
Save to open this file
MIT 6.S897: Machine Learning for Healthcare
All
- 01-What Makes Healthcare Unique?
01-What Makes Healthcare Unique?
- 02-Overview of Clinical Care
- 03-Deep Dive Into Clinical Data
- 04-Risk Stratification, Part 1
- 05-Risk Stratification, Part 2
- 06-Physiological Time-Series
- 07-Natural Language Processing (NLP), Part 1
- 08-Natural Language Processing (NLP), Part 2
- 09-Translating Technology Into the Clinic
- 10-Application of Machine Learning to Cardiac Imaging
- 11-Differential Diagnosis
- 12-Machine Learning for Pathology
- 13-Machine Learning for Mammography
- 14-Causal Inference, Part 1
- 15-Causal Inference, Part 2
- 16-Reinforcement Learning, Part 1
- 17-Reinforcement Learning, Part 2
- 18-Disease Progression Modeling and Subtyping, Part 1
- 19-Disease Progression Modeling and Subtyping, Part 2
- 20-Precision Medicine
- 21-Automating Clinical Work Flows
- 22-Regulation of Machine Learning and Artificial Intelligence in the US
- 23-Fairness
- 24-Robustness to Dataset Shift
- 25-Interpretability