EncartaLabs

Reinforcement Learning - Essentials

( Duration: 3 Days )

Reinforcement Learning (RL) is characterized by an agent continuously interacting and learning from a stochastic environment. Reinforcement Learning is a branch of Artificial Intelligence that formalizes this trial-and-error method of learning. RL is essentially the science of making sequential decisions. Reinforcement Learning is also a cross disciplinary subject that intersect with many disciplines of science such as optimal control, evolutionary learnings, dynamics programming etc.

The Reinforcement Learning - Essentials training course will teach you the fundamental concepts and techniques of various RL algorithms.

By attending Reinforcement Learning - Essentials workshop, delegates will learn to:

  • Understand and apply the fundamental concepts of reinforcement learning
  • Use RL on OpenAI Gym
  • Build value-based reinforcement learning systems
  • Build model-based reinforcement learning systems
  • Build policy-based reinforcement learning systems
  • Assess reinforcement learning systems and suggest more advanced reinforcement learning systems

  • Robotics Engineers
  • Machine Learning Developers
  • AI Practitioners

COURSE AGENDA

1

Introduction to Reinforcement Learning

  • What is Reinforcement Learning (RL)?
  • Markov Decision Process (MDP) and RL
  • Applications of RL
  • RL Algorithms Classifications
2

OpenAI Gym

  • What is OpenAI Gym
  • Install OpenAI Gym
  • OpenAI Gym Operations
3

Value Based Q-Learning

  • What is Q-Learning
  • Q Value and Q-Table
  • Bellman Equation
  • Q-Learning Algorithm
  • Epsilon Greedy Explore-Exploit Strategy
  • On-Policy vs Off-Policy Learning
  • What is SARSA?
  • SARSA Algorithm
4

Model-Based Learning

  • What is Model-Based Learnings
  • Model-Based Q-Learning Algorithms
5

Policy Valued Learning

  • Policy Based Methods
  • Policy Gradient Algorithm
  • Implementation of Policy Gradient Algorithm
6

Overview of Advanced RL Algorithms

  • Limitation of Value and Policy-Based Learnings
  • Actor-Critic Algorithms
  • Deep Reinforcement Algorithms

Encarta Labs Advantage

  • One Stop Corporate Training Solution Providers for over 4,000 Modules on a variety of subjects
  • All courses are delivered by Industry Veterans
  • Get jumpstarted from newbie to production ready in a matter of few days
  • Trained more than 50,000 Corporate executives across the Globe
  • All our trainings are conducted in workshop mode with more focus on hands-on sessions

View our other course offerings by visiting http://encartalabs.com/course-catalogue-all.php

Contact us for delivering this course as a public/open-house workshop/online training for a group of 10+ candidates.

Top