InfoCoBuild

CS 188: Introduction to Artificial Intelligence

CS 188: Introduction to Artificial Intelligence (Spring 2014, UC Berkeley). Instructor: Professor Pieter Abbeel. This course introduces the basic ideas and techniques underlying the design of intelligent computer systems. A specific emphasis will be on the statistical and decision-theoretic modeling paradigm. Topics include heuristic search, problem solving, game playing, knowledge representation, logical inference, planning, reasoning under uncertainty, expert systems, learning, perception, language understanding.

Lecture 10 - Reinforcement Learning

Go to the Course Home or watch other lectures:

Lecture 01 - Introduction

Lecture 02 - Uninformed Search

Lecture 03 - Informed Search: A* Search and Heuristics

Lecture 04 - Constraint Satisfaction Problems (CSPs)

Lecture 05 - Constraint Satisfaction Problems (cont.)

Lecture 06 - Adversarial Search: Game Trees, Minimax

Lecture 07 - Game Trees: Expectimax Search; Utilities

Lecture 08 - Markov Decision Processes

Lecture 09 - Markov Decision Processes (cont.)

Lecture 10 - Reinforcement Learning

Lecture 11 - Reinforcement Learning (cont.)

Lecture 12 - Probability

Lecture 13 - Markov Models

Lecture 14 - Hidden Markov Models (HMMs)

Lecture 15 - Applications of HMMs, Speech Recognition

Lecture 16 - Bayes' Nets: Representation

Lecture 17 - Bayes' Nets: Independence

Lecture 18 - Bayes' Nets: Inference

Lecture 19

Lecture 20 - Decision Networks and Value of Perfect Information

Lecture 21 - Machine Learning: Naive Bayes

Lecture 22 - Machine Learning: Perceptrons

Lecture 23 - Machine Learning: Kernels and Clustering

Lecture 24 - Advanced Applications: Natural Language Processing, Games, and Robotic Cars

Lecture 25 - Advanced Applications: Computer Vision and Robotics