Hands - On Reinforcement Learning with Python [Video]
This course has been retired. Check out the alternatives below
- $12.99 Video + Subscription Buy
-
What do you get with a Packt Subscription?
- Instant access to this title and 7,500+ eBooks & Videos
- Constantly updated with 100+ new titles each month
- Breadth and depth in over 1,000+ technologies
-
Getting Started With Reinforcement Learning Using OpenAI Gym
- The Course Overview
- Understanding Reinforcement Learning Algorithms
- Installing and Setting Up OpenAI Gym
- Running a Visualization of the Cart Robot CartPole-v0 in OpenAI Gym
-
Lights, Camera, Action – Building Blocks of Reinforcement Learning
- Exploring the Possible Actions of Your CartPole Robot in OpenAI Gym
- Understanding the Environment of CartPole in OpenAIGym
- Coding up Your First Solution to CartPole-v0
-
The Multi-Armed Bandit
- Creating a Bandit With 4 Arms Using Python and Numpy
- Creating an Agent to Solve the MAB Problem Using Python and Tensorflow
- Training the Agent, and Understanding What It Learned
-
The Contextual Bandit
- Creating an Environment With Multiple Bandits Using Python and Numpy
- Creating Your First Policy Gradient Based RL Agent With Tensorflow
- Training the Agent, and Understanding What It Learned
-
Dynamic Programming – Prediction, Control, and Value Approximation
- Visualizing Dynamic Programming in GridWorld in Your Browser
- Understanding Prediction Through Building a Policy Evaluation Algorithm
- Understanding Control Through Building a Policy Iteration Algorithm
- Building a Value Iteration Algorithm
- Linking It All Together in the Web-Based GridWorld Visualization
-
Markov Decision Processes and Neural Networks
- Understanding Markov Decision Process and Dynamic Programming in CartPole-v0
- Crafting a Neural Network Using Tensorflow
- Crafting a Neural Network to Predict the Value of Being in Different Environment States
- Training the Agent in CartPole-v0
- Visualizing and Understanding How Your Software Agent Has Performed
-
Model-Free Prediction & Control With Monte Carlo (MC)
- Running the Blackjack Environment From the OpenAI Gym
- Tallying Every Outcome of an Agent Playing Blackjack Using MC
- Visualizing the Outcomes of a Simple Blackjack Strategy
- Control – Building a Very Simple Epsilon-Greedy Policy
- Visualizing the Outcomes of the Epsilon-Greedy Policy
-
Model-Free Prediction & Control With Temporal Difference (TD)
- Visualizing TD and SARSA in GridWorld in Your Browser
- Running the GridWorld Environment From the OpenAI Gym
- Building a SARSA Algorithm to Find the Optimal Epsilon-Greedy Policy
- Visualizing the Outcomes of the SARSA