10-301 / 10-601Introduction to Machine Learning
Sign in
Lecture 1: Course OverviewLecture 2: Machine Learning as Function ApproximationLecture 3: Decision TreesLecture 4: Decision Tree Properties and HyperparametersLecture 5: k-Nearest Neighbor and Model SelectionLecture 6: PerceptronLecture 7: Linear RegressionLecture 8: Optimization for MLLecture 9: Stochastic Gradient Descent / Logistic RegressionLecture 10: Feature Engineering / RegularizationLecture 11: Neural NetworksLecture 12: Backpropagation ILecture 13: Backpropagation IILecture 14: Societal Impacts of ML (Evaluation)Lecture 15: PAC learningLecture 16: PAC Learning / MLE & MAPLecture 17: MLE & MAP / CNNs and RNNsLecture 18: RNN-LMs and Transformers-LMsLecture 19: Transformers, AutoDiff, Pre-training, Fine-TuningLecture 20: In-context Learning / Reinforcement Learning: MDPsLecture 21: Reinforcement Learning: Core AlgorithmsLecture 22: Reinforcement Learning: Policy Gradient / Deep RLLecture 23: Unsupervised Learning: Autoencoders / PCA / K-MeansLecture 24: Recommender Systems / Matrix FactorizationLecture 25: Ensemble Methods: Boosting & BaggingLecture 26: Special Topics: Coding Agents / Generative Models for Vision

Reinforcement Learning › In-context Learning / Reinforcement Learning: MDPs

Lecture 20: In-context Learning / Reinforcement Learning: MDPs

Wed, Nov 4

Readings

  • Reinforcement Learning: A Survey. Kaelbling, et al (1996).

Unit: Reinforcement Learning

Poll 20
PDF not available
PDF not available