Login using Social Account
Login using your credentials
In this video, we will understand:
what is credit assignment problem
what is policy gradients algorithm
how to implement policy gradients algorithm in training the agent, to play the CartPole game
Taking you to the next exercise in seconds...
Stay here Next Exercise
Want to create exercises like this yourself? Click here.
Error
1 What is Reinforcement Learning?
2 What is the objective of this project?
3 WorkFlow
4 Step 1 - Import the Modules
5 Importing the Modules
6 Step 2 - Understanding OpenAI Gym
7 Introduction to OpenAI Gym
8 Introduction to OpenAI gym environment
9 Understanding CartPole game of OpenAI gym
10 Let's make the agent play the game!
11 Step 3 - Hard-code simple Policy
12 A simple hard-coded policy
13 Step 4 - Neural Network for the Game
14 Building the Neural Network
15 Game with untrained neural network
16 Training the Neural Network
17 Step 5 - Understanding Policy Gradients
18 Policy Gradients
19 Credit Assignment Problem
20 Step 6 - Implementing Policy Gradients
21 Defining play_one_step function
22 Defining play_multiple_episodes function
23 Defining the discount function and normalizing function
24 Training with Policy Gradients
Loading comments...