Title: An Alternative Approach for Playing Complex Games like Chess.
1An Alternative Approach for Playing Complex Games
like Chess.
Jan Lemeire May 19th 2008
2Computer versus Brain
Research Topics
Deep Blue 600 million evaluations/second
Chess experts 10 patterns/second
3Brute force chess playing
Most succesful!
Evaluation of future states
Alternative Game Playing Approach
3
4Alternative game playing approaches
- Decision-making used to map states to operators.
- Explanation-Based Learning (EBL) try to learn
the states that lead to advantageous situations. - States are identified by patterns.
5Game State Evaluation
- All approaches rely on a game state evaluation
- measure goodness of state
- Or
- to select a good move.
My hypothesis is based on a problem with state
evaluation.
6Example fork pattern.
Opportunity! Fork pattern is way to success!
Counter move Fork pattern does not give an
advantage
7Correct evaluation problem
- Consider two relevant patterns, P1 and P2
- evaluation f(P1, P2)
- 4 regions in state space should be considered
For example fork and make chess
8Correct evaluation problem
- Evaluation f(features or patterns).
- One has to capture all situations in which the
pattern leads to a successful outcome, all
counter plans have to be excluded. - Evaluation of pattern combinations heavily
depends on game context! - Features alone do not give us the right
information.
9Known problem in literature
- Deep Blue relied on looking as far as possible
into the future and just a simple state
evaluation. - However, even simple patterns like a knight fork
are non-trivial to formalize Fürnkranz 2001. - Learning too many too specialized rules with
explanation-based learning, Minton 1984,
Epstein, Gelfand and Joanna Lesniak 1996 (HOYLE
pattern-based learning). - Even in simple games, such as tic-tac-toe, 45
concepts were learned with 52 exception clauses,
Fawcett and Utgoff 1991.
9
10Hypothesis
- The impact of a pattern on the outcome of the
game entirely depends on whether or not some
states, called the effects, are attained during
the continuation of the game.
11New kind of knowledge
- Fork ? win a piece
- Weak kings defense ? successful attack on the
king - Pressure ? successful combination
Patterns denote opportunities, advantages have to
be verified.
Alternative Game Playing Approach
11
E.g. fork bad defense of the king can we have a
successful attack on the king or get an advantage
by putting pressure on the king bad defense ?
pressure ? advantage
12Alternative game playing
White recognizes pattern 1 White has to
check in game tree whether - a positive effect
can be attained - black can neutralize pattern
1
Hypothesis More efficient than brute force tree
exploration
- Second hypothesis this works if one can quickly
evaluate interfering patterns
13Similar to human game playing!
- Chess experts rely on falsification (Cowley and
Byrne, 2004). - Humans can easily recognize and identify
patterns, but have difficulties formally defining
them. - Humans can pinpoint the patterns that were
decisive in a game, can answer why-questions. - not by current computer game playing
- Humans can reason about a game.
14Hypothesis requires theoretical or experimental
confirmation
- Test
- by simulation of games ? no decisive conclusion
yet. - Pattern engine needed that is able to
- Describe patterns
- Recognize patterns
- Extract patterns
- Reason with patterns
- White attacks two black pieces with a fork, one
of the pieces can make chess. White thus has to
move its king and black can bring his second
piece into safety. - Theoretical proof?