Experience-Based Chess Play Robert Levinson Machine Intelligence Lab University

Experience-Based Chess Play Robert Levinson Machine Intelligence Lab University www.phwiki.com

Experience-Based Chess Play Robert Levinson Machine Intelligence Lab University

Josey, Amos, News Director has reference to this Academic Journal, PHwiki organized this Journal Experience-Based Chess Play Robert Levinson Machine Intelligence Lab University of Cali as long as nia, Santa Cruz Stan as long as d ML Seminar March 16, 2005 Outline Review of State-of-the-art in Games Review of Computer Chess Method Blindspots in addition to Unsolved Issues ================== 4. Morph 4a. Philosophy in addition to Results 4b. Patterns/Evaluation 4c. Learning Td-learning Neural Nets Genetic Algorithms Why Chess Human/computer approaches very different Most studied game Well-known internationally in addition to by public Cognitive studies available Accurate, well-defined rating system ! Complex in addition to Non-Uni as long as m John McCarthy, Alan Turing, Claude Shannon, Herb Simon in addition to Ken Thompson in addition to . Game theoretic value unknown Active Research Community/Journal

Aristotle University of Thessaloniki GR www.phwiki.com

This Particular University is Related to this Particular Journal

State of the art State of the art (2) State of the art (3)

Kasparov vs. Deep Blue 1. Deep Blue can examine in addition to evaluate up to 200,000,000 chess positions per second Garry Kasparov can examine in addition to evaluate up to three chess positions per second 2. Deep Blue has a small amount of chess knowledge in addition to an enormous amount of calculation ability. Garry Kasparov has a large amount of chess knowledge in addition to a somewhat smaller amount of calculation ability. 3. Garry Kasparov uses his tremendous sense of feeling in addition to intuition to play world champion-calibre chess. Deep Blue is a machine that is incapable of feeling or intuition. 4. Deep Blue has benefitted from the guidance of five IBM research scientists in addition to one international gr in addition to master. Garry Kasparov is guided by his coach Yuri Dokhoian in addition to by his own driving passion to play the finest chess in the world. 5. Garry Kasparov is able to learn in addition to adapt very quickly from his own successes in addition to mistakes. Deep Blue, as it st in addition to s today, is not a “learning system.” It is there as long as e not capable of utilizing artificial intelligence to either learn from its opponent or “think” about the current position of the chessboard. 6. Deep Blue can never as long as get, be distracted or feel intimidated by external as long as ces (such as Kasparov’s infamous “stare”). Garry Kasparov is an intense competitor, but he is still susceptible to human frailties such as fatigue, boredom in addition to loss of concentration. Recent Man vs. Machine Matches Garry Kasparov versus Deep Junior, January 26 – February 7, 2003 in New York City, USA. Result: 3 – 3 draw. Evgeny Bareev versus Hiarcs-X, January 28 – 31 , 2003 in Maastricht, Netherl in addition to s. Result: 2 – 2 draw. Vladimir Kramnik versus Deep Fritz, October 2 – 22, 2002 in Manama, Bahrain. Result: 4 – 4 draw. Minimax Example terminal nodes: values calculated from some evaluation function Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 Max

other nodes: values calculated via minimax algorithm Max Max Min Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 4 7 6 2 6 3 4 5 1 2 5 4 1 2 6 3 4 3 Max Max Min Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 4 7 6 2 6 3 4 5 1 2 5 4 1 2 6 3 4 3 7 6 5 5 6 4 Max Max Min Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 4 7 6 2 6 3 4 5 1 2 5 4 1 2 6 3 4 3 7 6 5 5 6 4 5 3 4

Max makes first move down the left h in addition to side of the tree, in the expectation that countermove by Min is now predicted. After Min makes move, tree will need to be regenerated in addition to the minimax procedure re-applied to new tree Max Max Min Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 4 7 6 2 6 3 4 5 1 2 5 4 1 2 6 3 4 3 7 6 5 5 6 4 5 3 4 5 Actual move made by Max Possible later moves Max Max Min Min 4 7 9 6 9 8 8 5 6 7 5 2 3 2 5 4 9 3 4 7 6 2 6 3 4 5 1 2 5 4 1 2 6 3 4 3 7 6 5 5 6 4 5 3 4 5 Computer chess Let’s say you start with a chess board set up as long as the start of a game. Each player has 16 pieces. Let’s say that white starts. White has 20 possible moves: The white player can move any pawn as long as ward one or two positions. The white player can move either knight in two different ways. The white player chooses one of those 20 moves in addition to makes it. For the black player, the options are the same: 20 possible moves. So black chooses a move. Now white can move again. This next move depends on the first move that white chose to make, but there are about 20 or so moves white can make given the current board position, in addition to then black has 20 or so moves it can make, in addition to so on.

Chess complexity There are 20 possible moves as long as white. There are 20 20 = 400 possible moves as long as black, depending on what white does. Then there are 400 20 = 8,000 as long as white. Then there are 8,000 20 = 160,000 as long as black, in addition to so on. If you were to fully develop the entire tree as long as all possible chess moves, the total number of board positions is about 1,000,000,000,000,000,000,000,000, 000,000,000,000,000,000,000,000,000,000,000,000,000,000, 000,000,000,000,000,000,000,000,000,000,000,000,000,000, 000,000,000,000, or 10120. There have only been 1026 nanoseconds since the Big Bang. There are thought to be only 1075 atoms in the entire universe. How computer chess works No computer is ever going to calculate the entire tree. What a chess computer tries to do is generate the board-position tree five or 10 or 20 moves into the future. Assuming that there are about 20 possible moves as long as any board position, a five-level tree contains 3,200,000 board positions. A 10-level tree contains about 10,000,000,000,000 (10 trillion) positions. The depth of the tree that a computer can calculate is controlled by the speed of the computer playing the game. Is computer chess intelligent The minimax algorithm alternates between the maximums in addition to minimums as it moves up the tree. This process is completely mechanical in addition to involves no insight. It is simply a brute as long as ce calculation that applies an evaluation function to all possible board positions in a tree of a certain depth. What is interesting is that this sort of technique works pretty well. On a fast-enough computer, the algorithm can look far enough ahead to play a very good game. If you add in learning techniques that modify the evaluation function based on past games, the machine can even improve over time. The key thing to keep in mind, however, is that this is nothing like human thought. But does it have to be

Leaf nodes examined Search Depth Hmmm. What to do Black is to move: Ra5! White to move:

What is strategy the art of devising or employing plans or stratagems toward a goal where favorable.

Josey, Amos WPGG-AM News Director www.phwiki.com

Chess is Multi-Level Science Would you say a traditional chess program’s chess strength is based mainly on a firm axiomatic theory about the strengths in addition to balances of competing differential semiotic trajectory units in a multiagent hypergeoemetric topological manifold-like zero-sum dynamic environment or simply because it is an accurate short-term calculator! Morph Philosophy Rein as long as cement Learning Mathematical View of Chess Don’t Cheat!!!

Cheating! define DOUBLED-PAWN-PENALTY 10 define ISOLATED-PAWN-PENALTY 20 define BACKWARDS-PAWN-PENALTY 8 define PASSED-PAWN-BONUS 20 define ROOK-SEMI-OPEN-FILE-BONUS 10 define ROOK-OPEN-FILE-BONUS 15 define ROOK-ON-SEVENTH-BONUS 20 / the values of the pieces / int piece-value[6] = 100,300,350,500,900,0 White-Queen-square table Goal: ELO 3000+ 2800+ World Champion 2600+ GM 2400+ IM 2200+ FM (> 99 percent) Expert 1600 Median (> 50 percent) 1543 Morph 1000 Novice (beginning tournament player) 555 R in addition to om

Future Experiments We are confident we can achieve higher ELO rating levels using GA but it is important we do not cheat (provide specific chess knowledge) Variations upon the Knowledge Representation, including X-Tuple Neighborhood Networks Evolving meta-parameters using Genetic Algorithms e.g. range of mutating weights, size of knowledge representation, ofbrains competing Lamarckian Evolution: Learning during a generation (not just selection/mutation alone) i.e., TD updating Using GA with alternative Knowledge Representations including various Neural Net configurations Gr in addition to master Database Database: all (507,734 games) Report: 1.d4 Nf6 2.Bg5 Ne4 3.h4 (173 games) ECO: A45s [Trompowsky: Raptor Variation] Generated by Scid 3.0, 2001.11.15 1. STATISTICS AND HISTORY —- 1.1 Statistics Games 1-0 =-= 0-1 Score ——— All report games 173 61 44 68 47.9% Both rated 2600+ 0 0 0 0 0.0% Both rated 2500+ 17 8 5 4 61.7% Both rated 2400+ 33 16 9 8 62.1% Both rated 2300+ 67 26 21 20 54.4%

Josey, Amos News Director

Josey, Amos is from United States and they belong to WPGG-AM and they are from  Evergreen, United States got related to this Particular Journal. and Josey, Amos deal with the subjects like Local News; National News; Regional News

Journal Ratings by Aristotle University of Thessaloniki

This Particular Journal got reviewed and rated by Aristotle University of Thessaloniki and short form of this particular Institution is GR and gave this Journal an Excellent Rating.