Master Reinforcement Learning With These 3 Projects

Too locked in to realize my hair was sticking up most the time

Resources:
https://github.com/ALucek/three-RL-projects
https://gymnasium.farama.org/
https://huggingface.co/learn/deep-rl-course/

Chapters:
00:00 - Intro
00:52 - What Is Reinforcement Learning?
03:48 - Q-Learning: Introduction
05:33 - Q-Learning: Environment Setup
07:46 - Q-Learning: Hyperparameters Explained
11:09 - Q-Learning: Defining Rewards
13:18 - Q-Learning: e-greedy strategy
14:04 - Q-Learning: The Bellman Equation
17:18 - Q-Learning: Training Script
18:07 - Q-Learning: Visualization & Evaluation
20:33 - Deep Q Networks: Introduction
21:28 - Deep Q Networks: Environment Setup
24:22 - Deep Q Networks: Neural Network Setup
25:38 - Deep Q Networks: Agent Setup
26:01 - Deep Q Networks: Experience Replay
28:15 - Deep Q Networks: Q-Target Stabilization
31:15 - Deep Q Networks: Double DQN
32:58 - Deep Q Networks: Hyperparameters & Training
34:03 - Deep Q Networks: Visualization & Evaluation
36:41 - Value-Based vs Policy Based Reinforcement Learning
38:14 - Proximal Policy Optimization: Introduction
41:45 - Proximal Policy Optimization: Environment Setup
43:39 - Proximal Policy Optimization: Image Preprocessing & Stacking
46:55 - Proximal Policy Optimization: Neural Network Architecture
37:53 - Proximal Policy Optimization: Surrogate Objective Function
50:47 - Proximal Policy Optimization: Value Function Loss & Entropy Bonus
51:46 - Proximal Policy Optimization: Creating the Model
53:39 - Proximal Policy Optimization: Training
54:46 - Proximal Policy Optimization: Evaluation & Visualization
57:27 - Tie Back to LLM RLHF

#ai #machinelearning #programming