1.1 1.zip
1. 1 Structure of the First Project
2.1 2.zip
2. 2 Understand How Bellman Equation Works
3.1 3.zip
3. 3 Understand Why We are Using GYM Library
4.1 4.zip
4. 4 Get the state and action numbers with code
5.1 5.zip
5. 5 Understand Why we are using deque
6.1 6.zip
6. 6 Understand the Q-Table
7.1 7.zip
7. 7 Understand Exploration and Exploitation trade-off
8.1 8.zip
8. 8 Choose an action based on the current observation
9.1 9.zip
9. 9 Apply the action and get the next observation, reward, and done flag
10.1 10.zip
10. 10 Store the experience in the deque and Update the Q-table
11.1 11.zip
11. 11 Make the Agent take action according to Q-Table
12.1 12.zip
12. 12 Solve FrozenLake 8x8 map
13.1 13.zip
13. 13 Understand how deep learning works
14. 14 Using value 1 for Learning Rate in Bellman equation
15. 15 Simplify the Bellman Eq
16. 16 Input Size
17. 17 The Logic of the optimizing parameters of DQN Model
18.1 18.zip
18. 18 Define the model and print weight and bias
19.1 19.zip
19. 19 Learn how to calculate the output with funtions
20.1 20.zip
20. 20 Define Hyperparameters
21.1 21 ADAM OPTIMIZER.pdf
21. 21 Understand the Math of ADAM OPTIMIZER
22.1 22.zip
22. 22 Find best action with the model
23.1 23.zip
23. 23 Make training time shorter
24.1 24.zip
24. 24 Taking sample from memory to optimize the model
25.1 25.zip
25. 25 Learn how to optimize
26.1 26.zip
26. 26 Show the performance of the Model
