-
Recent Posts
Recent Comments
Archives
- March 2020
- May 2019
- December 2018
- June 2018
- December 2017
- October 2017
- July 2017
- June 2017
- May 2017
- March 2017
- February 2017
- January 2017
- August 2016
- July 2016
- May 2016
- April 2016
- March 2016
- February 2016
- December 2015
- November 2015
- September 2015
- August 2015
- July 2015
- June 2015
- April 2015
- March 2015
- February 2015
- January 2015
- November 2014
- October 2014
- September 2014
- August 2014
- July 2014
- June 2014
- May 2014
- April 2014
- March 2014
- February 2014
- January 2014
- December 2013
- November 2013
- October 2013
- September 2013
- August 2013
- July 2013
- June 2013
- May 2013
- April 2013
- March 2013
- February 2013
- January 2013
- December 2012
- November 2012
- October 2012
- September 2012
- August 2012
- July 2012
- June 2012
- May 2012
- April 2012
- March 2012
- February 2012
Categories
-
Join 53 other subscribers
MyCalendar
Meta
Monthly Archives: March 2012
Solving a Boundary Value Problem in MATLAB – An Example
In this post, I demonstrate a simple function to solve a BVP problem. Here the problem is an ODE. After solving the problem, we plot the result. Copy- paste , all the below code into an m-file in MATLAB and … Continue reading
Posted in Linux, Machine Learning, MATLAB, programming, Software, Ubuntu
Tagged boundary, boundary condition, boundary value problem, bvp, code, example, linux, Matlab, ode, ordinary differential equation, programming, sample, simple, software, solve, windows
Leave a comment
Rewards VS. Values (in the concept of Reinforcement Learning)
In the concept of Reinforcement Learning, we usually deal with two pretty similar keywords, reward and value, that can be confusing for beginners. In this brief post, I will mention the differences and actual definitions of these terms. Rewards are … Continue reading
Elements
elements of Unsupervised Learning (Reinforcement Learning) 1-Agent (behaviour at a given time) 2-Environment 3-Policy 4-Value Function (specifies what is good in the long run) 5-Reward Function (Define Goal – what is good in an immediate sense) 6-Model of the environment … Continue reading
General Categorization of Machine Learning methods
There are three main branches of learning methods: 1-Supervised learning – These methods require labeled data to learn from. For instance given a 10000 images of cats and dogs which are labeled correctly by a supervisor, a machine learning approach … Continue reading
Posted in Machine Learning, Neural Networks, Reinforcement Learning, Robotics, Thoughts
Tagged action, anomaly detection, bayes, bayes classifier, classification, classifier, clustering, data, direct policy search, fuzzy, gaussian, gaussian process, k-means, label, labeled, Machine Learning, neural networks, observation, q-learning, radial basis network, Reinforcement Learning, reward, sarsa, state, supervised, supervised learning, td-learning, unsupervised, unsupervised learning
Leave a comment
Policy Function – definition
(An Introduction to Reinforcement Learning) – Part.1 Policy Function: defines action related to a state / maps any state to a related action. There are three kinds of Policies: 1- Stochastic Policy: (probability – uses a transition function that … Continue reading
Posted in Machine Learning, Reinforcement Learning, Robotics
Tagged Machine Learning, Policy, Reinforcement Learning, Robotics
Leave a comment