MATH4060 Intro to Markov Chain and Reinforcement Learning 2022 - All lectures
42 videos • 1,669 views • by Dr Mihai Nica
1
MATH4060 Zoom class 2022-01-10
Dr Mihai Nica
Download
2
MATH4060 Zoom class 2022-01-12
Dr Mihai Nica
Download
3
MATH4060 Zoom class 2022-01-14
Dr Mihai Nica
Download
4
MATH4060 Zoom class 2022-01-19
Dr Mihai Nica
Download
5
MATH4060 Zoom class 2022-01-21
Dr Mihai Nica
Download
6
MATH4060 Zoom class 2022-01-24
Dr Mihai Nica
Download
7
MATH4060 Zoom class 2022-01-26
Dr Mihai Nica
Download
8
MATH4060 Zoom class 2022-01-28
Dr Mihai Nica
Download
9
MATH4060 Async class 2022-01-31: 1 Derivation of Bellman Equation
Dr Mihai Nica
Download
10
MATH4060 Async class 2022-01-31: 2 Value Iteration Algorithm
Dr Mihai Nica
Download
11
MATH4060 Async class 2022-01-31: 3 Value Iteration for Optimal Strategy in PIG version 1
Dr Mihai Nica
Download
12
MATH4060 Async class 2022-01-31: 4 Value Iteration for Optimal Strategy in PIG version 2
Dr Mihai Nica
Download
13
MATH4060 Async class 2022-01-31: 5 Optimal Strategy in PIG version 3
Dr Mihai Nica
Download
14
MATH4060 Async class 2022-02-07 Part 1: Live coding Gambler's Problem Ex 4.3 with Value Iteration
Dr Mihai Nica
Download
15
MATH4060 Async class 2022-02-07 Part 2: Bonus video: Making it run without loops by matrices/einsum
Dr Mihai Nica
Download
16
MATH4060 Async class 2022-02-08: Bonus Bonus video: the theoretical optimal strategies
Dr Mihai Nica
Download
17
MATH4060 Zoom class 2022-02-09
Dr Mihai Nica
Download
18
MATH4060 Zoom class 2022-02-11
Dr Mihai Nica
Download
19
MATH4060 Live class 2022-02-14: Greedy policy improvement
Dr Mihai Nica
Download
20
MATH4060 Live class 2022-02-16: Introduction to Temporal Difference Learning
Dr Mihai Nica
Download
21
MATH4060 Async class : 2022-02-18 Part 1 Example of some TD learning
Dr Mihai Nica
Download
22
MATH 4060 Async class: 2022-02-18 Part 2 Intro to the SARSA algorithm (TD learning for the policy!)
Dr Mihai Nica
Download
23
MATH4060 Async class 2022-02-18 Part 3 Live Coding SARSA algorithm for the Gambler's Problem
Dr Mihai Nica
Download
24
MATH4060 Live class 2022-02-28 : SARSA recap and intro to off policy and Q learning
Dr Mihai Nica
Download
25
MATH*4060 Live Class 2022-03-02 Part 1: Q learning and testing Q learning vs SARSA (see description)
Dr Mihai Nica
Download
26
MATH*4060 Live class 2022-03-02 Part 2 Intro to why we need gradient descent
Dr Mihai Nica
Download
27
MATH*4060 Live class 2022-03-04: Intro to Gradient Descent
Dr Mihai Nica
Download
28
MATH*4060 Live class 2022-03-07 Using stochastic gradient descent for Value Functions
Dr Mihai Nica
Download
29
MATH*4060 Live class 2022-03-09 Linear Features
Dr Mihai Nica
Download
30
MATH*4060 Live class 2022-03-11 Final Project and Can't Stop
Dr Mihai Nica
Download
31
MATH*4060 Live Class 2022-03-14 Policy Based methods (Video cut off after 15 min sorry!)
Dr Mihai Nica
Download
32
MATH*4060 Live class 2022-03-18 Deep neural networks for our policy
Dr Mihai Nica
Download
33
MATH*4060 Live class 2022-03-16 Actor Critic methods
Dr Mihai Nica
Download
34
MATH*4600 Live class 2022-03-21 Introduction to multi-arm bandits
Dr Mihai Nica
Download
35
MATH*4060 Live class 2022-03-25 Multiarm Bandits Regret Calculations
Dr Mihai Nica
Download
36
MATH*4060 Live Class 2022-03-28 Optimizing amount to explore and Upper Confidence Bound Bandits
Dr Mihai Nica
Download
37
MATH*4060 Live class 2022-03-30 Live coding Multi-armed bandit simulator and testing the algos
Dr Mihai Nica
Download
38
Live class 2022-04-01 Discussion about actor critic and final project
Dr Mihai Nica
Download
39
MATH*4060 2022-04-04 Live class: Game tree based methods and alpha beta pruning
Dr Mihai Nica
Download
40
MATH*4060 2022 04 06 Live class: Random rollouts, Monte Carlo tree search and AlphaZero
Dr Mihai Nica
Download
41
Some live final project coding 2022 04 07 14 36 34
Dr Mihai Nica
Download
42
Can't Stop Tournament Results
Dr Mihai Nica
Download