Full Report for Chameleons by Chris Huntoon

Full Report for Chameleons by Chris Huntoon

Generated at 23/07/2021, 03:01 from 1000 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!

Play

Chameleons can move in all eight directions. There are two types of movement: a step and a jump.

Step
moving to an adjacent empty space.
Jump
A piece can jump over an opponent's piece and remove it from the game, if that opposing piece is adjacent and the space beyond it is empty, as in Checkers. And just like Checkers, jumps are mandatory and multiple jumps are possible. If having a choice of possible jumps, a player need not pick the one with the most captures.

Color Change

If a player ends his turn with one of his Chameleons on a space of the opposing color, he has until the beginning of his next turn to move it to a space of his own color. If he does not, that piece changes color to match it's space and effectively switches sides.If a player moves that Chameleon from a space of the opposing color to another space of the opposing color, then it changes color when landing on that space. If a player starts a turn with a Chameleon on a space of an opposing color, but then uses another Chameleon to perform a series of jumps, the Chameleon on the opposing color will flip after the first jump, as the player has signaled that he won't be moving it.

The central, space is always considered the opposite color of the Chameleon that occupies it. Thus if a Chameleon is left on that space, after the original player has had a turn to move it, it will begin changing colors every turn. It will then match the color of the player whose turn it is.

Goal

The object to the game is to completely eliminate your opponent's Chameleons, either through capture or color change.

Miscellaneous

General comments:

Play: Combinatorial

Family: Line games

Mechanism(s): Line

BGG Stats

BGG EntryChameleons
BGG Ratingnull
#Votersnull
SDnull
BGG Weightnull
#Votersnull
Yearnull

Kolomogorov Complexity Analysis

Size (bytes)25493
Reference Size10293
Ratio2.48

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 second25517.69 (39.19µs/playout)
Reference Size1555935.90 (0.64µs/playout)
Ratio (low is good)60.97

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

LabelIts/sSDNodes/sSDGame lengthSD
Random playout25,8984741,985,08736,1097713
search.UCT27,2911,3791000

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: Green win %49.80±3.09Includes draws = 50%
2: Red win %50.20±3.09Includes draws = 50%
Draw %99.20Percentage of games where all players draw.
Decisive %0.80Percentage of games with a single winner.
Samples1000Quantity 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

MatchAIStrong WinsDrawsStrong Losses#GamesStrong Scorep1 Win%Draw%p2 Win%Game Length
0Random         
1UCT (its=2)5711192709600.6262 <= 0.6568 <= 0.686144.7912.4042.8177.53
3UCT (its=4)5012592279870.6084 <= 0.6388 <= 0.668237.1826.2436.5881.94
5UCT (its=30)471319198090.7495 <= 0.7794 <= 0.806630.1639.4330.4187.91
6UCT (its=80)313635239710.6188 <= 0.6493 <= 0.678716.7965.4017.8294.48
8UCT (its=594)39746708640.6992 <= 0.7297 <= 0.758322.9254.0523.0388.88
9
UCT (its=1614)
88
911
1
1000
0.5125 <= 0.5435 <= 0.5741
5.30
91.10
3.60
98.05
10
UCT (its=1614)
6
981
13
1000
0.4656 <= 0.4965 <= 0.5274
0.90
98.10
1.00
99.65

Search for levels ended. Close to theoretical value: draw.

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 length99.79 
Branching factor14.50 
Complexity10^95.51Based on game length and branching factor
Computational Complexity10^6.60Sample quality (100 best): 21.56
Samples1000Quantity 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 actions552Number of distinct moves (e.g. "e4") regardless of position in game tree
Killer moves32A 'killer' move is selected by the AI more than 50% of the time
Too many killers to list.
Good moves340A good move is selected by the AI more than the average
Bad moves207A bad move is selected by the AI less than the average
Terrible moves11A terrible move is never selected by the AI
Terrible moves: a5-a3xa4,e1-c1xd1,b1-d1xc1,a7-a5xa6,f1-d1xe1,c7-e7xd7,a1-c1xb1,g3-g5xg4,c2-e2xd2,f6-d6xe6,d7-b7xc7
Response distance3.37Mean distance between move and response; a low value relative to the board size may mean a game is tactical rather than strategic.
Samples1000Quantity of logged games played

Board Coverage

A mean of 91.25% of board locations were used per game.

Colour and size show the frequency of visits.

Game Length

Game length frequencies.

Mean98.80
Mode[99]
Median99.0

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.)

Red: removal, Black: move, Blue: Add, Grey: pass, Purple: swap sides, Brown: other.

Openings

MovesAnimation
b6-d4xc5,a3-c5xb4,a1-a3xa2,c4-a2xb3,a3-a1xa2,e2-c4xd3,b5-d3xc4,d2-b4xc3,d4-b6xc5,b7-b5xb6
b6-d4xc5,a5-c5xb5,d3-b5xc4,f5-d3xe4,d4-b6xc5,c7-c5xc6,c5-a5xb5,a5-c7xb6,e6-e4xe5,e4-c6xd5
b6-d4xc5,a5-c5xb5,d3-b5xc4,f5-d3xe4,d4-b6xc5,c7-c5xc6,c5-a5xb5,a5-c7xb6,e6-c4xd5,c2-e4xd3
b6-d4xc5,a5-c5xb5,d3-b5xc4,f5-d3xe4,d4-b6xc5,c7-a5xb6,a5-c5xb5,c5-c7xc6,e6-e4xe5,e4-c6xd5
b6-d4xc5,a5-c5xb5,d3-b5xc4,f5-d3xe4,d4-b6xc5,c7-a5xb6,a5-c5xb5,c5-c7xc6,e6-c4xd5,c2-e4xd3
b6-d4xc5,c7-c5xc6,d4-b6xc5,e5-c7xd6,e4-c6xd5,a3-c5xb4,c1-a3xb2,d2-d4xd3,d4-b2xc3,b2-b4xb3
b6-d4xc5,c7-c5xc6,e4-c6xd5,e5-c7xd6,d4-b6xc5,a3-c5xb4,c1-a3xb2,d2-d4xd3,d4-b2xc3,b2-b4xb3
b6-d4xc5,c7-c5xc6,e4-c6xd5,f7-d5xe6,g4-e6xf5,e6-e4xe5,e4-g4xf4,d2-f4xe3,d4-b6xc5,a5-c7xb6
b6-d4xc5,c7-c5xc6,e4-c6xd5,f7-d5xe6,g4-e6xf5,e6-e4xe5,e4-g4xf4,c5-c7xc6,c7-e5xd6,d4-d6xd5
b6-d4xc5,c7-c5xc6,e4-c6xd5,f7-d5xe6,g4-e4xf4,e4-e6xe5,e6-g4xf5,d2-f4xe3,d4-b6xc5,a5-c7xb6
b6-d4xc5,c7-c5xc6,e4-c6xd5,f7-d5xe6,g4-e4xf4,e4-e6xe5,e6-g4xf5,c5-c7xc6,c7-e5xd6,d4-d6xd5
d6-d4xd5,f3-d5xe4,c6-e4xd5,f7-d5xe6,d5-f3xe4,g4-e6xf5,e6-e4xe5,e4-g4xf4,a6-c6xb6,b4-d6xc5

Opening Heatmap

Colour shows the success ratio of this play over the first 10moves; black < red < yellow < white.

Size shows the frequency this move is played.

Unique Positions Reachable at Depth

012345678910
14197842322631282275271461459278607116853971

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 10.