Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

22
Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto
  • date post

    21-Dec-2015
  • Category

    Documents

  • view

    221
  • download

    3

Transcript of Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Page 1: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Inside HARUKA

Written by Ryuichi Kawa

Surveyed by Akihiro Kishimto

Page 2: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Obstacles to Go-Playing Programs

• So many exceptions that must be implemented:– E.g. A & B are connected, B & C are

connected, but A & C aren’t

• Static evaluation v.s. search– If possible, evaluate statically– If exceptions frequently appears, perform a

search

Page 3: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Overview of HARUKA’s Search Engine

• 6 routines– Fuseki– Joseki– Life and death– Semeai– Search around center– Local search

• Each routine returns move and evaluation value called deiri(input/output) computation

1. Compute value by my playing first2. Compute value by opponent playing first3. Compute 1. – 2. And return this value

Page 4: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Fuseki Routine

• Inaccurate but looks stable with occasional adjustments– Each fuseki move has evaluation values:

• Three-four point, star point: 18 points

• Kakari: 17 points

• Corner enclosure: 16 points

• Extension, splitting move etc: 8-15 points based on distance and strength of stones

Page 5: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Joseki Routine

• Pattern sized 11 * 11– Immediately makes a move if pattern matches– Randomly choose one if more than one pattern

matches

• Pattern matches with smaller sizes (9 * 9 or 7 * 7)– Regard as promising move– Passed to local search engine

Page 6: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Life and Death/Semeai Routines

• Return status (e.g. win, win for Ko, seki) of life and death/semeai

• Occasionally returns incorrect outcome– E.g. stones outside of region influences on

outcome

• Might be only a part of local search engine?

Page 7: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Search around Center

• Perform 3-ply search for points extending/fighting/breaking moyo around center of the board– # of branches <= 10– Choose point that doesn’t contain any stones

for 8 directions

• Prepared for programs playing like Go++• Currently does not work well

Page 8: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Overview of Local Search

• Search range– (x,y): stone worth considering– R = {(p,q)| |p – x| + |q – y| < 8}– Ladder is an exception

• Alpha-beta search– Maximum number of branches = 10– Depth = direct 3-5 ply search– Spends almost all the time

Page 9: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Overview of Local Search (cont’d)

• How is a local search performed?1. Do a local search around the opponent’s stone played

last time

2. Do a local search around the stone I played last time

3. Compute places that are influenced on by these two stones

4. Perform local searches around these places

5. Previous results are stored and updated

6. Re-searches are performed if necessary

Page 10: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Position Recognition (1 / 3)

• From simple notion to complicated (19 features)– Whether there’s a stone or not, # of empty stones around

a point, ko point– Strings and # of stones, liberties (up to 4) , # of liberties– Characteristics of connections

• 1-point jump, 2-point jump, knight’s move, knight’s big move

– Detect points where opponent can’t cut • kosumi, bamboo, eye, opponent’s suicide point

– Points where ate/nuki is possible– Points where cut/fukurami is possible

Page 11: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Position Recognition (2 / 3)

– Status on whether white and black stones are adjacent

– Points for connections (1-point jump peep, keima-dekiri), double atari

– Capture search

– Kiri(cut) search (reuse capture search)

– Life and death for semi-connected strings and influence computation

– Eye-shape (eye, half-eye, eye with 2 (3, 4, ..) consecutive moves, false-eye)

Page 12: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Position Recognition (3 / 3)

– Detect groups– Compute boundary and size of moyo for each group– Compute how easily group can be escaped and

connection to other groups– Strength, size and importance of group– Compute evaluation values for moves played at the

points adjacent to stones • hane, nobi, attach, ate,cut, tsuki-nuke, pincer-attach, etc

– Compute evaluation values for moves played at the points not adjacent to stones

• 1-point jump, kosumi, keima-gake, hazama, sarusuberi, etc

Page 13: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Capture Search

• Alpha-beta search + TT for string with # of liberties <= 4– # of branches <= 8– Depth <= 64 – # of node limit <= 1000

• Performs well if # of liberties <= 3• Needs a lot of time (sometimes 90% of computation) to

determine outcome• Cannot distinguish unconditional capture from capture for ko• Need to restrict moves and prove strings aren’t captured as

quickly as possible

Page 14: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Kiri Search

• Detect whether target strings are cut at cutting points– Utilize capture search

• Stones dropped at cutting points are captured target strings are not cut

• Perform only at important points (capture search too)– points around stone played in the previous

move

Page 15: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Influence Computation

• Preliminary compute life and death (strength) of stones

• Compute influence: c / d^2– c: strength of stone d: distance– Influenced up to 1-point jump point– Can’t go through other stones and bamboo

• Add up these numbers

Page 16: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Strength and Importance of Groups

• Convert features into # of eye points– # of eye points– Eye-shape– Possibility to escape, extend, and connect– Status of opponent’s stones

Page 17: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Evaluating Points (Not) Adjacent to Stones

• Have value between 0 – 255 tuned by hand– 0: completely bad move– 64: bad move– 128: normal move– …

• Used if all the stones in the region are (mostly) alive

Page 18: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Move Generation

• Moves are generated in the following order:1. Moves having a high priority

• connecting stones around stone played by opponent just before, escaping from atari, 2-line block

2. Double atari, capture, escape3. Semeai moves4. Attacking/defending weak stones5. Moves at points (not) adjacent to stones having high

evaluation values6. Ko threats

• Look at the whole board

Page 19: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Evaluation at Leaf Nodes

1. Position recognition

2. Verifying if one of two strings can be captured

3. Detecting Life and death status for group

4. Adjusting life and death status for group considering connections to other groups

5. Adjusting life and death status for group considering opponent’s groups and semeai

6. Territory computation

Page 20: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Other Issues

• Adjustment to search results– Adding 1-4 points for sente move– Effective for yose

Page 21: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Near Future Work

• Play moves that prevents opponent’s moyo• Adjust evaluation values for yose

considering double-sente, sente, double-gote

• Have a strategy for detecting a loss• Perform 5-ply search without degrading

speed (realization probability?)• Improve capture search

Page 22: Inside HARUKA Written by Ryuichi Kawa Surveyed by Akihiro Kishimto.

Things that Must be Done in the Long Run

• Strategies based on position evaluation– There’s no difference of losses between 0.5

point and 100 points

• Human-like playing style– Consistency, moves when in a disadvantageous

position

• Special scheme for ko fights– Seems to be impossible with searches only