Hands - On Reinforcement Learning with Python

BY
Udemy

Mode

Online

Fees

₹ 449 3499

Quick Facts

particular details
Medium of instructions English
Mode of learning Self study
Mode of Delivery Video and Text Based

Course and certificate fees

Fees information
₹ 449  ₹3,499
certificate availability

Yes

certificate providing authority

Udemy

The syllabus

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 OpenAI Gym
  • 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 Process 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
  • Training the Agent in CartPole-v0
  • Visualizing and Understanding How Your Software Agent Has Performed

Model-Free Prediction and 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 and 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

Trending Courses

Popular Courses

Popular Platforms

Learn more about the Courses