Currently viewing the category: "Machine Learning"

Stanford Reinforcement Learning lectures

by admin on December 22, 2010 · 109 Comments

On 22th of December I watched videos of Machine learning lectures focused on Reinforcement Learning. Lectuer: Associate Professor Andrew Ng, Stanford University Applications of Reinforcement Learning, Markov Decision Process (MDP), Defining Value & Policy Functions, Value Function, Optimal Value Function, Value Iteration, Policy Iteration (watch on YouTube) Generalization to Continuous States, Discretization & Curse of [...]

Object reaching with Reinforcement Learning

by admin on November 26, 2010 · 104 Comments

The goal of this post is to capture my progress in learning of object reaching on my iCub. Suppose iCub stands in the front of the object, which is placed on a table, so the robot can reach it without moving other joints than these on one arm. iCub has to set its arm joint [...]