Full Report for SLLUG(7x7,0-3,1.5 Komi,Opponent) by Stephen Tavener
Full Report for SLLUG(7x7,0-3,1.5 Komi,Opponent) by Stephen Tavener
Inspired by Slitherlink, but ended up more like Libraria.
Generated at 03/10/2020, 04:44 from 124856 logged games.
Rules
Representative game (in the sense of being of mean length). Wherever you see the 'representative game' referred to in later sections, this is it!
Setup
Put a random number in each square of the grid.
Play
Each turn, draw a line on the edge of an unclaimed square, or pass.
After placing, check any neighbouring squares to see if they are claimed; a square is claimed if it has exactly as many neighbouring lines as the number in it. The player with the most neighbouring lines claims the number. In the case of a tie, the non-moving player gets the number.
Goal
The game ends when both players pass in succession. Players add their claimed numbers, and the highest score wins. Draws are possible, but rare.
Balance
To offset the first player advantage, 1.5 komi seems to work well.
Ai Ai calculates the size of the implementation, and compares it to the Ai Ai implementation of the simplest possible game (which just fills the board). Note that this estimate may include some graphics and heuristics code as well as the game logic. See the wikipedia entry for more details.
Playout Complexity Estimate
Playouts per second
12366.06 (80.87µs/playout)
Reference Size
204687.34 (4.89µs/playout)
Ratio (low is good)
16.55
Tavener complexity: the heat generated by playing every possible instance of a game with a perfectly efficient programme. Since this is not possible to calculate, Ai Ai calculates the number of random playouts per second and compares it to the fastest non-trivial Ai Ai game (Connect 4). This ratio gives a practical indication of how complex the game is. Combine this with the computational state space, and you can get an idea of how strong the default (MCTS-based) AI will be.
Playout/Search Speed
Label
Its/s
SD
Nodes/s
SD
Game length
SD
Random playout
226
12
13,691
726
61
7
search.UCB
15,230
1,014
56
3
search.UCT
15,243
996
57
3
Random: 10 second warmup for the hotspot compiler. 100 trials of 1000ms each.
Other: 100 playouts, means calculated over the first 5 moves only to avoid distortion due to speedup at end of game.
Mirroring Strategies
Rotation (Half turn) lost each game as expected.
Reflection (X axis) lost each game as expected.
Reflection (Y axis) lost each game as expected.
Copy last move lost each game as expected.
Mirroring strategies attempt to copy the previous move. On first move, they will attempt to play in the centre. If neither of these are possible, they will pick a random move. Each entry represents a different form of copying; direct copy, reflection in either the X or Y axis, half-turn rotation.
Win % By Player (Bias)
1: White win %
48.96±0.28
Includes draws = 50%
2: Black win %
51.04±0.28
Includes draws = 50%
Draw %
0.00
Percentage of games where all players draw.
Decisive %
100.00
Percentage of games with a single winner.
Samples
124856
Quantity of logged games played
Note: that win/loss statistics may vary depending on thinking time (horizon effect, etc.), bad heuristics, bugs, and other factors, so should be taken with a pinch of salt. (Given perfect play, any game of pure skill will always end in the same result.)
Note: Ai Ai differentiates between states where all players draw or win or lose; this is mostly to support cooperative games.
UCT Skill Chains
Match
AI
Strong Wins
Draws
Strong Losses
#Games
Strong Score
p1 Win%
Draw%
p2 Win%
Game Length
0
Random
1
UCT (its=2)
631
0
359
990
0.6069 <= 0.6374 <= 0.6667
48.69
0.00
51.31
60.53
5
UCT (its=6)
631
0
350
981
0.6127 <= 0.6432 <= 0.6726
46.69
0.00
53.31
59.69
16
UCT (its=17)
631
0
361
992
0.6057 <= 0.6361 <= 0.6655
48.08
0.00
51.92
60.04
26
UCT (its=27)
631
0
343
974
0.6173 <= 0.6478 <= 0.6772
49.90
0.00
50.10
59.64
38
UCT (its=39)
631
0
306
937
0.6427 <= 0.6734 <= 0.7027
48.24
0.00
51.76
59.42
51
UCT (its=52)
631
0
351
982
0.6121 <= 0.6426 <= 0.6719
46.84
0.00
53.16
59.23
64
UCT (its=65)
623
0
377
1000
0.5925 <= 0.6230 <= 0.6525
48.10
0.00
51.90
58.96
65
UCT (its=65)
504
0
496
1000
0.4731 <= 0.5040 <= 0.5349
50.40
0.00
49.60
59.14
Search for levels ended: time limit reached.
Level of Play: Strong beats Weak 60% of the time (lower bound with 95% confidence).
Draw%, p1 win% and game length may give some indication of trends as AI strength increases.
1st Player Win Ratios by Playing Strength
This chart shows the win(green)/draw(black)/loss(red) percentages, as UCT play strength increases. Note that for most games, the top playing strength show here will be distinctly below human standard.
Complexity
Game length
59.44
Branching factor
52.81
Complexity
10^94.34
Based on game length and branching factor
Samples
124856
Quantity of logged games played
Computational complexity (where present) is an estimate of the game tree reachable through actual play. For each game in turn, Ai Ai marks the positions reached in a hashtable, then counts the number of new moves added to the table. Once all moves are applied, it treats this sequence as a geometric progression and calculates the sum as n-> infinity.
Move Classification
Distinct actions
113
Number of distinct moves (e.g. "e4") regardless of position in game tree
Good moves
17
A good move is selected by the AI more than the average
Bad moves
96
A bad move is selected by the AI less than the average
Samples
124856
Quantity of logged games played
Board Coverage
A mean of 0.00% of board locations were used per game.
Colour and size show the frequency of visits.
Game Length
Game length frequencies.
Mean
59.44
Mode
[61]
Median
60.0
Change in Material Per Turn
This chart is based on a single representative* playout, and gives a feel for the change in material over the course of a game. (* Representative in the sense that it is close to the mean length.)
Actions/turn
Table: branching factor per turn, based on a single representative* game. (* Representative in the sense that it is close to the mean game length.)
Action Types per Turn
This chart is based on a single representative* game, and gives a feel for the types of moves available throughout that game. (* Representative in the sense that it is close to the mean game length.)
This chart shows the best move value with respect to the active player; the orange line represents the value of doing nothing (null move).
The lead changed on 20% of the game turns. Ai Ai found 2 critical turns (turns with only one good option).
Position Heatmap
This chart shows the relative temperature of all moves each turn. Colour range: black (worst), red, orange(even), yellow, white(best).
Good/Effective moves
Measure
All players
Player 1
Player 2
Mean % of effective moves
26.92
25.09
28.82
Mean no. of effective moves
3.97
3.23
4.72
Effective game space
10^17.22
10^7.47
10^9.75
Mean % of good moves
33.47
62.38
3.57
Mean no. of good moves
14.22
24.70
3.38
Good move game space
10^35.30
10^30.34
10^4.96
These figures were calculated over a single game.
An effective move is one with score 0.1 of the best move (including the best move). -1 (loss) <= score <= 1 (win)
A good move has a score > 0. Note that when there are no good moves, an multiplier of 1 is used for the game space calculation.
Quality Measures
Measure
Value
Description
Hot turns
81.36%
A hot turn is one where making a move is better than doing nothing.
Momentum
28.81%
% of turns where a player improved their score.
Correction
30.51%
% of turns where the score headed back towards equality.
Depth
3.03%
Difference in evaluation between a short and long search.
Drama
0.24%
How much the winner was behind before their final victory.
Foulup Factor
6.78%
Moves that looked better than the best move after a short search.
Surprising turns
0.00%
Turns that looked bad after a short search, but good after a long one.
Last lead change
66.10%
Distance through game when the lead changed for the last time.
Decisiveness
15.25%
Distance from the result being known to the end of the game.
These figures were calculated over a single representative* game, and based on the measures of quality described in "Automatic Generation and Evaluation of Recombination Games" (Cameron Browne, 2007). (* Representative, in the sense that it is close to the mean game length.)
Unique Positions Reachable at Depth
0
1
2
3
1
105
10365
508420
Note: most games do not take board rotation and reflection into consideration. Multi-part turns could be treated as the same or different depth depending on the implementation. Counts to depth N include all moves reachable at lower depths. Inaccuracies may also exist due to hash collisions, but Ai Ai uses 64-bit hashes so these will be a very small fraction of a percentage point.
Shortest Game(s)
No solutions found to depth 3.
Puzzles
Puzzle
Solution
White to win in 11 moves
White to win in 7 moves
Black to win in 7 moves
White to win in 8 moves
White to win in 9 moves
White to win in 8 moves
Black to win in 8 moves
White to win in 8 moves
Black to win in 7 moves
White to win in 7 moves
Weak puzzle selection criteria are in place; the first move may not be unique.
12872818047648824264.png)
_trajectory.png)
_coverMap.png)
_lengths.png)
_owner_counts.png)
.png)
_owner_counts.png)
_trajectory.png)
_temperature_ranges.png)
11485544623718938797.png)
11485544623718938797.gif)
14700395559163649249.png)
14700395559163649249.gif)
2903251099332020424.png)
2903251099332020424.gif)
256956399727696452.png)
256956399727696452.gif)
12355603611895745138.png)
12355603611895745138.gif)
8497283088897685810.png)
8497283088897685810.gif)
6804485022644720220.png)
6804485022644720220.gif)
5799114734470645557.png)
5799114734470645557.gif)
11221711872530625571.png)
11221711872530625571.gif)
5521518064804040794.png)
5521518064804040794.gif)