37:46

CS885 Module 6: Inverse RL

23:28

CS885 Module 5: Distributional RL

28:42

CS885 Module 4: Partially Observable Reinforcement Learning

30:20

CS885 Module 3: Imitation Learning

41:48

CS885 Module 2: Maximum Entropy Reinforcement Learning

22:18

CS885 Module 1: Trust region & proximal policy optimization

01:14:55

CS480/680 Lecture 24: Gradient boosting, bagging, decision forests

01:05:23

CS480/680 Lecture 23: Normalizing flows (Priyank Jaini)

01:07:24

CS480/680 Lecture 22: Ensemble learning (bagging and boosting)

55:51

CS480/680 Lecture 21: Generative networks (variational autoencoders and GANs)

38:58

CS480/680 Lecture 20: Autoencoders

01:22:38

CS480/680 Lecture 19: Attention and Transformer Networks

01:40:41

CS480/680 Lecture 18: Recurrent and recursive neural networks

01:01:31

CS480/680 Lecture 17: Hidden Markov Models

01:15:18

CS480/680 Lecture 16: Convolutional neural networks

01:31:06

CS480/680 Lecture 15: Deep neural networks

28:42

CS480/680 Lecture 14: Support vector machines (continued)

01:17:43

CS480/680 Lecture 13: Support vector machines

01:11:15

CS480/680 Lecture 12: Gaussian Processes

01:16:14

CS480/680 Lecture 11: Kernel Methods

01:29:21

CS480/680 Lecture 10: Multi-layer neural networks and backpropagation

01:16:23

CS480/680 Lecture 9: Perceptrons and single layer neural nets

01:34:44

CS480/680 Lecture 8: Logistic regression and generalized linear models

01:00:59

CS480/680 Lecture 7: Mixture of Gaussians

06:24

CS480/680 Lecture 6: Model compression for NLP (Ashutosh Adhikari)

09:17

CS480/680 Lecture 6: EM and mixture models (Guojun Zhang)

08:58

CS480/680 Lecture 6: Sum-product networks (Pranav Subramani)

08:31

CS480/680 Lecture 6: Fact checking and reinforcement learning (Vik Goel)

09:13

CS480/680 Lecture 6: Unsupervised word translation (Kira Selby)

08:49

CS480/680 Lecture 6: Normalizing flows (Priyank Jaini)

06:00

CS480/680 Lecture 6: Kaggle datasets and competitions

09:59

CS480/680 Lecture 6: Tools for surveys (Paulo Pacheco)

01:13:25

CS480/680 Lecture 5: Statistical Linear Regression

01:10:47

CS480/680 Lecture 4: Statistical Learning

51:00

CS480/680 Lecture 3: Linear Regression

01:29:23

CS480/680 Lecture 2: K-nearest neighbours

01:04:49

CS480/680 Lecture 1: Course Introduction

03:12

Online Structure Learning for Feedforward and Recurrent Sum-Product Networks

18:08

CS885 Lecture 18b: Learning Driving Styles for Autonomous Vehicles (Presenter: Marko Ilievski)

21:03

CS885 Lecture 20b: Memory augmented control networks (Presenter: Aravind Balakrishnan)

22:36

CS885 Lecture 20a: Neural map: structured memory for deep RL (Presenter: Andreas Stöckel)

47:27

CS885 Lecture 19c: Memory Augmented Networks

14:39

CS885 Lecture 19b: Learning cooperative visual dialog agents (Presenter: Nalin Chhibber)

17:10

CS885 Lecture 19a: End-to-end LSTM based dialog control (Presenter: Hamidreza Shahidi)

27:40

CS885 Lecture 18a: Safe multi-agent RL for autonomous driving (Presenter: Ashish Gaurav)

32:59

CS885 Lecture17c: Inverse Reinforcement Learning

14:19

CS885 Lecture 17b: Control of a Quadrotor (Presenter Nicole McNabb)

24:35

CS885 Lecture 17a: Target-Driven Visual Navigation (Presenter: James Cagalawan)

21:09

CS885 Lecture 16b: FeUdal Networks for Hierarchical RL (Presenter: Rene Bidart)

14:53

CS885 Lecture 16a: The Option-Critic Architecture (Presenter: Zebin Kang)

36:05

CS885 Lecture 15c: Semi-Markov Decision Processes

18:14

CS885 Lecture 15b: Proximal Policy Optimization (Presenter: Ruifan Yu)

22:34

CS885 Lecture 15a: Trust Region Policy Optimization (Presenter: Shivam Kalra)

20:19

CS885 Lecture 14c: Trust Region Methods

24:40

CS885 Lecture 14b: Mastering Chess and Shogi (Presenter: Kira Selby)

26:35

CS885 Lecture 14a: Mastering the Game of Go (Presenter: Henry Chen)

31:57

CS885 Lecture 13c: Adversarial Search

20:34

CS885 Lecture 13b: Lifelong Learning in Minecraft (Presenter: Yetian Wang)

20:18

CS885 Lecture 13a: Playing FPS Games with Deep RL (presenter: Mark Iwanchyshyn)

28:11

CS885 Lecture 12: Deep Recurrent Q-Networks