Intro to Markov Chains and Reinforcement Learning W2024
17 videos • 1,388 views • by Dr Mihai Nica
Recording of Lectures on Markov Chains and Reinforcement Learning
1
What is Reinforcement Learning? Lecture with 4 Examples | Intro to Markov Chains and RL
Dr Mihai Nica
Download
2
Snakes+Ladders probability problem in spreadsheet and Python | Intro to Markov Chains Lec 2
Dr Mihai Nica
Download
3
Two state Markov chain example and the steady state distribution | Intro to Markov Chains Lecture 3
Dr Mihai Nica
Download
4
Solving probabilities and expected values for Markov Chains & the (baby) Bellman Eqn | Intro to RL
Dr Mihai Nica
Download
5
Creating Markov chains by enlarging the state space & Baby Bellman Eqn | Intro Markov Chains and RL
Dr Mihai Nica
Download
6
Markov Chains with actions & dice game PIG | Intro to Markov Chains and Reinforcement Learning
Dr Mihai Nica
Download
7
The Bellman Equation and 1 Player PIG solved with Value Iteration | Intro to Markov Chains and RL
Dr Mihai Nica
Download
8
Live coding the Gambler's Problem using Value Iteration | Intro to Markov Chains and Reinforcement L
Dr Mihai Nica
Download
9
[ Lecture ] Intro to Monte Carlo methods in Reinforcement Learning | Intro to Markov Chains and RL
Dr Mihai Nica
Download
10
[Lecture] Monte Carlo evaluation and control: A Gridworld Example | Intro to Markov Chains and RL
Dr Mihai Nica
Download
11
[Lecture] Intro to Temporal Different Learning TD learning | Intro to Markov Chains and RL
Dr Mihai Nica
Download
12
Learning the Q function (SARSA and Q-learning) and Intro to Multi armed Bandits | Intro to RL
Dr Mihai Nica
Download
13
Multiarmed bandits, Analysis of the Explore-first-Exploit-later and Upper Confidence Bound Algorithm
Dr Mihai Nica
Download
14
SARSA vs Q-learning with epsilon-greedy action selection | Intro to Markov Chains and RL
Dr Mihai Nica
Download
15
Replacing Value Tables with Parametrized Functions | Intro to Markov Chains and RL
Dr Mihai Nica
Download
16
Gradient Descent for Learning the Value Function Gradient Monte Carlo and Semi-gradient TD learning
Dr Mihai Nica
Download
17
Lab 3 Solutions and Ideas/Life-Pro-Tips for the Final Project
Dr Mihai Nica
Download