Course description
Machine Learning: Reinforceable Learning - E-learning from Udacity
This e-learning course is designed to guide learners through Reinforced Learning, a machine learning task concerned with the actions that software agents ought to take in order to maximize rewards. Participants will gain valuable reinforcement learning approaches, such as the Markov Decision Processes and Game Theory.
A graduate level program
This Supervised Learning course is the second of three in the Machine Level series offered in cooperation with Georgia Tech. The primary outcome from this second course is to enable learners in an undersstanding of behavioral psychology crucial for reward maximization
Do you work at this company and want to update this page?
Is there out-of-date information about your company or courses published here? Fill out this form to get in touch with us.
Upcoming start dates
Who should attend?
This intermediate level Machine Learning: Reinforced Learning course is designed for development professionals hoping to gain a comprehensive understanding of the topics and methods involved in Supervised Learning.
Pre-Requisites
This is the second course in a series of three on machine learning. Along with completion of the first course in the series, Machine Learning: Supervised Learning, participants will also have a basic understanding of probability theory, statistics, some programming and ideally an introduction to artificial intelligence.
Find out if this course is right for you - request more information here!
Training content
Training topics for this Machine Learning: Reinforced Learning course include:
Projects:
Use a familiar Gridworld domain to train a Reinforcement Learning agent and then design an agent that can play Pacman!
Lessons:
Markov Decision Processes
- Decision Making and Reinforcement Learning
- Markov Decision Processes
- Sequences of Rewards
- Assumptions
- Policies
- Finding Policies
Reinforcement Learning
- Rat Dinosaurs
- API
- Three Approaches to RL
- A New Kind of Value Function
- Estimating Q from Transitions
- Q Learning Convergence
- Greedy Expoloration
Game Theory
- What is Game Theory
- Minimax
- Fundamental Result
- Game Tree
- Von Neumann
- Center Game
- Snitch
- A Beautiful Equilibrium
- The Two Step
- 2Step2Furious
Game Theory, Continued
- The Sequencing
- Iterated Prisioner’s Dilemna
- Uncertain End
- Tit for Tat
- Finite State Strategy
- Folk Theorem
- Security Level Profile
- Grim Trigger
- Implausible Threats
- Pavlov
- Computational Folk Theorem
- Stochastic Games and Multiagent RL
- Zero Sum Stochastic Games
- General Sum Games
- Reinforcement Learning Project
Costs
It is free to start this Machine Learning: Reinforced Learning course
Estimated time for completion assuming 6 hours per week: Approx. 1 months
2-Week Free Trial: Love it or Leave it
All Udacity courses are offered with a two-week free trial. Learners will have plenty of time to make sure that the program fits their needs. If it's not working out for any reason - user can cancel their subscription fee of charge.