Aliens School
Cinematic Knowledge Experience
0%
Aliens School
Now Playing
Aliens School ยท HIEN
โŒจ๏ธ Keyboard Shortcuts
โ†’Next slide โ†Previous slide SpacePlay / Pause MNarration on/off FFullscreen ?Show/hide this
Press any key to close
Skill Topic ยท Cinematic

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna!

Aliens School โ€” AI Series #78 Hinglish mein Reinforcement Learning samjho! ๐Ÿš€

Overview
๐ŸŒŸ

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna! โ€” Quick Facts

๐Ÿ“Œ

Algorithm: Type

๐ŸŽฏ

Q-Learning: Value

โšก

DQN: Value

๐Ÿ”‘

PPO: Policy

Topic 1
๐Ÿ“š

๐Ÿ’ก Reinforcement Learning Kya Hai?

๐Ÿ“š ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ RL = Reinforcement Learning โ”‚ โ”‚ โ”‚ โ”‚โ€ฆ
Topic 2
โœจ

๐Ÿ“Š ML Types Comparison

๐Ÿ’ก ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ SUPERVISED LEARNING: โ”‚ โ”‚ Teacher:โ€ฆ
Topic 3
๐Ÿ“ฅ โš™๏ธ ๐Ÿ”ฌ ๐Ÿ’ก

๐Ÿง  Key Components

๐ŸŽฏ ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ ๐Ÿค– AGENT = learner / decision maker โ”‚โ€ฆ
Topic 4
โญ

๐ŸŽฎ Classic Example: Grid World

โญ ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ Agent (๐Ÿค–) ko Goal (๐Ÿ†) tak pahunchnaโ€ฆ
Topic 5
โœจ

๐Ÿ“ Key Concepts

๐Ÿ”‘ Exploration vs Exploitation ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚โ€ฆ
Topic 6
๐Ÿ“ฅ ๐Ÿ“ฅ ๐Ÿง  ๐Ÿ”ฌ ๐Ÿ’ก ๐ŸŽฏ

๐Ÿ”ง Q-Learning Algorithm

โœจ ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ Q-TABLE = "cheat sheet" for agent โ”‚โ€ฆ
Topic 7
๐Ÿ”’

๐Ÿ—๏ธ RL Algorithms Family

๐ŸŒŸ ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ VALUE-BASED: โ”‚ โ”‚ โ†’ Q-Learning (tableโ€ฆ
Topic 8
๐Ÿš€

๐ŸŒ Famous RL Achievements

๐Ÿš€ ` โ”Œโ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ”€โ” โ”‚ ๐ŸŽฎ ATARI (2013-2015, DeepMind): โ”‚ โ”‚โ€ฆ
Topic 9
๐Ÿ“ฅ โš™๏ธ ๐Ÿ”ฌ ๐Ÿ’ก

๐Ÿ’ป JavaScript Example

๐Ÿ“š `javascript // Q-Learning: Grid World class QLearningAgent { constructor(states, actions,โ€ฆ
Topic 10
โœจ

โ“ Quiz

๐Ÿ’ก

a) Labeled data se

๐Ÿ”‘

b) Trial and error + rewards se โœ…

โšก

c) Clustering se

๐ŸŽฏ

a) 100% exploration

Quick Quiz
๐Ÿง  QUIZ TIME

Quiz โ€” Question 1

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna! ka sabse sahi definition kya hai?

Quick Quiz
๐Ÿง  QUIZ TIME

Quiz โ€” Question 2

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna! ka 'Q-Learning' kya hai?

Complete! ๐ŸŽ‰
COMPLETE

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna! Complete!

Aliens School ยท HIEN ยท Cinematic Knowledge

โœ…

๐ŸŽฎ Reinforcement Learning โ€” Reward Se Seekhna! Complete

1/15
0:00
REC 00:00ESC=Cancel
Aliens School
3
Recording shuru hone wali hai...
โœ…
Recording Complete
Video process ho rahi hai...
Live Class
Slide 1 / 7
Timer
00:00
๐Ÿ“ Speaker Notes
โ€”
โญ๏ธ Up Next
โ€”
โ€”
๐Ÿ—‚๏ธ All Slides