Agent Framework

As part of my ongoing agent training, I re-read the agent environment algorithm in Chapter 2 of AIMA (Russell and Norvig, 1995). The key challenge is how to convert an algorithm with repeat and for loops into viable Prolog code. At first inspection, the implementation is best suited for a language with control loops built into the programming language (e.g., LISP). My primary Prolog books [Bratko 1990] and [Sterling and Shapiro 1994] did not provide the required help. However, upon rereading Prolog Programming In Depth (Covington, Nute, and Vellino 1997), I was able to figure out how to write loops.

Blocks World

In order to understand the RRL paper better, I began to review the blocks world.  So I went back to review [Luger & Stubblefield 1993] on the discussions on the blocks world.  It was mostly used to illustrate propositional and predicate calculus.  In addition, there was a section on robotic planning using the frame problem and STRIPS as tools.  I reviewed the code base for robotic planning written in prolog.  So I began to enumerate all the possible states in the three blocks world.  Afterwards, I designed an test on how to move from an initial state to goal state.  I wrote the initial state, the action, the next state, etc. until the goal state was achieved.  Indeed, this was very simple for three blocks.

Progress Report – October 2009

In this month, I continued my studies in Relational Reinforcement Learning by reviewing the article Towards Informed Reinforcement Learning from the proceedings of the 2004 Machine Learning workshop of Relational Reinforcement Learning.   Basically the articles summarizes that an agent with limited information can find an optimal policy and can achieve a goal or goal states with limited information about its environment.  The experiments reported seems to suggest this type of exploration is possible.  According to Google Scholar search, there are 11 subsequent articles that reference this one.  In the RRL arena, my goal is to repeat the block’s world experiment as reported in Relational Reinforcement Learning article by Dzeroski, De Raedt, and Blockeel.

Progress Report – September 2009

This month marks my first year in utilizing wordpress to host my blog.  It has been a great journey so far and hopefully will be better this coming year.

The month of September has been busy.  Unfortunately I did not write any blog entries due to my busy schedule.  However, from statistical point of view, my blog had the second highest total of number of views (362 in total).  Also, I covered various topics this month with Probability and Statistics, Bayesian Inference, Reinforcement Learning, and finally a LISP review.

I started to review the Reinforcement Learning book (Sutton and Barto 1997) only reading Part 1 and part of Part 2.  I did download the lisp code associated with the book.  I ran the tic-tac-toe program in my test environment.

Progress Report – August 2009

During the month of August, I focused on Relational Reinforcement Learning, a field that combines Relational Learning and Reinforcement Learning fields.  Please read my blog entry for Relational Reinforcement Learning.  Afterwards, I have read a number of different articles regarding RRL learning from different authors, including the RRL workshop at the ICML 2004 conference.  My initial preference is the work performed and researched by Dr. Eduardo F. Morales.

I posted my review and comments regarding part I of the book The Art of Prolog (Sterling and Shapiro 1994).  There are very few books regarding Logic Programming in recent years.  Since the mid 1990s, much of the effort in Logic Programming has been with Inductive Logic Programming and Relational Learning.  The emerging field of Statistical Relational Learning has become a new field of research. 

Reinforcement Learning

I finally completed the Summer Schools in Logic and Learning (SSLL 09) video lecture for Reinforcement Learning presented by Scott Sanner.  It was a good introduction into Reinforcement Learning.  It is a six part lecture.  Plan for time to watch the videos.  He starts with an introduction into the topic.  Next is model based solutions with Markov Decision Process (MDP) and dynamic programming (DP) with value iteration and policy iteration.  The Bellman equations are introduced.  Lastly, he reviews model free approaches from Chapters 5, 6, and 7 of the Reinforcement Learning: An Introduction (Sutton and Barto 1998).  He covers Monte Carlo and Temporal Difference (TD) algorithms, in particular TD lamdba and SARSA.  However due to large state spaces of problems, he discussion function approximators (both linear and nonlinear) along with gradient descend approaches.  A worth while video lecture.

Warnsdorf Algorithm

As part of my follow research to my paper, I did some preliminary research for the Warnsdorf’s algorithm for finding knight’s tours.  I found three relevant papers on the subject (Pohl 1967, Pohl-Stockmeyer 2004, and Ganzfried 2004).  Basically, the Warnsdorf algorithm is to traverse the path with least degree.  In the case of a tie, the a path is randomly selected.  In reality, the Warnsdorf algorithm is not consistently successful as pointed out by (Ganzfried 2004).  The (Ganzfried 2004) paper modifies the Warnsdorf algorithm with key squares in which the move order changes, which improves finding knight tours.  The next step is generate a prolog program using the Pohl-Warnsdorf and Ganzfried algorithms.

Relational Reinforcement Learning

I start this month reading the articles in Relational Reinforcement Learning.  It began as a curiosity due to a response in the Reinforcement Learning mailing list.  The authors point a speech by Rich Sutton and Leslie Pack Kaelbling at the IJCAI 1997 conference in Japan, in which they recommended the combination of Induction Logic Programming (aka Relational Learning) and Reinforcement Learning.  The authors of the paper demonstrate this concept by using the blocks world domain to illustrate the combination of both fields.  Perhaps, this is exactly what I needed since I have done much reading, studying, and video lectures with logic programming, ILP, and reinforcement learning.  Of course, this paper spawn much researching according to CiteSeerX and Google Scholarly.

I found the web site to the 2004 Workshop in Relational Reinforcement Learning and downloaded the proceedings.

I shall continue this path of research interest.

Progress Report – July 2009

In this progress report, I attended the ICAI 09 conference in Las Vegas (the IJCAI 2009 is located in Pasadena).  I presented my work on A Brute Force Approach to Solving the Knights Tour Using Prolog.  One thing that I learned is the participants are proud to share their work with others.  Another lesson is to make your presentation within the time allotted.  A few presenters did not finish their presentations in the 20 minutes time slot.  I rehearsed my presentation a few times to have the timing within 20 minutes.  I also learned that I need to get more training with MS Power Point.

I am also continue to view the video lectures from the Summer Schools in Logic and Learning from Video Lectures.  Thus, I have completed the Intelligent Agents video lectures by John Lloyd. 

AIMA Part VI

Part VI of the AIMA book covers learning and various techniques on agents can learn.  The material covers Learning from Observations, Neural Networks, Reinforcement Learning, and Knowledge in Learning.  In the second edition, the chapter in Neural Networks is replaced with Statistical Learning Methods.

I read Chapter 18 of the AIMA book called Learning from Observations.  The Chapter focuses on decision trees and decision lists as some computational learning theory.  The main classification algorithm is the ID3 algorithm for classifying examples and generating decision trees.  The ID3 algorithm is based on Hunt’s Concept Learning System (CLS).  The ID3 algorithm uses information theory for obtaining the decision tree covering most the examples.  I have studied the ID3 algorithm quite extensively since the original application was to classify the winning position in the king and rook versus the king and knight endgame (Quinlan 1983).