Skip to content

Commit 14c763f

Browse files
marcharpermarcharper
committed
Normalize CMDs for evolvers and rewrite with common function names
1 parent 47c9c03 commit 14c763f

File tree

6 files changed

+591
-409
lines changed

6 files changed

+591
-409
lines changed

‎README.md

Lines changed: 91 additions & 53 deletions
Original file line numberDiff line numberDiff line change
@@ -44,36 +44,43 @@ overfitting.
4444
## Optimization Functions
4545

4646
There are three objective functions:
47-
* Maximize mean match score over all opponents with `objective_match_score`
48-
* Maximize mean match score difference over all opponents with `objective_match_score_difference`
49-
* Maximize Moran process fixation probability with `objective_match_moran_win`
47+
* Maximize mean match score over all opponents with `objective_score`
48+
* Maximize mean match score difference over all opponents with `objective_score_difference`
49+
* Maximize Moran process fixation probability with `objective_moran_win`
50+
51+
Parameters for the objective functions can be specified in the command line
52+
arguments for each evolver.
5053

5154
## Running
5255

5356
### Look up Tables
5457

5558
```bash
5659
$ python lookup_evolve.py -h
57-
Lookup Evolve.
60+
Lookup Table Evolver
5861

5962
Usage:
60-
lookup_evolve.py [-h] [-p PLAYS] [-o OPP_PLAYS] [-s STARTING_PLAYS]
61-
[-g GENERATIONS] [-k STARTING_POPULATION] [-u MUTATION_RATE] [-b BOTTLENECK]
62-
[-i PROCESSORS] [-f OUTPUT_FILE] [-z INITIAL_POPULATION_FILE] [-n NOISE]
63+
lookup_evolve.py [-h] [--generations GENERATIONS] [--population POPULATION]
64+
[--mu MUTATION_RATE] [--bottleneck BOTTLENECK] [--processes PROCESSORS]
65+
[--output OUTPUT_FILE] [--objective OBJECTIVE] [--repetitions REPETITIONS]
66+
[--noise NOISE] [--nmoran NMORAN]
67+
[--plays PLAYS] [--op_plays OP_PLAYS] [--op_start_plays OP_START_PLAYS]
6368

6469
Options:
65-
-h --help show this
66-
-p PLAYS number of recent plays in the lookup table [default: 2]
67-
-o OPP_PLAYS number of recent plays in the lookup table [default: 2]
68-
-s STARTING_PLAYS number of opponent starting plays in the lookup table [default: 2]
69-
-g GENERATIONS how many generations to run the program for [default: 500]
70-
-k STARTING_POPULATION starting population size for the simulation [default: 20]
71-
-u MUTATION_RATE mutation rate i.e. probability that a given value will flip [default: 0.1]
72-
-b BOTTLENECK number of individuals to keep from each generation [default: 10]
73-
-i PROCESSORS number of processors to use [default: 1]
74-
-f OUTPUT_FILE file to write data to [default: tables.csv]
75-
-z INITIAL_POPULATION_FILE file to read an initial population from [default: None]
76-
-n NOISE match noise [default: 0.00]
70+
-h --help Show help
71+
--generations GENERATIONS Generations to run the EA [default: 500]
72+
--population POPULATION Starting population size [default: 10]
73+
--mu MUTATION_RATE Mutation rate [default: 0.1]
74+
--bottleneck BOTTLENECK Number of individuals to keep from each generation [default: 5]
75+
--processes PROCESSES Number of processes to use [default: 1]
76+
--output OUTPUT_FILE File to write data to [default: lookup_tables.csv]
77+
--objective OBJECTIVE Objective function [default: score]
78+
--repetitions REPETITIONS Repetitions in objective [default: 100]
79+
--noise NOISE Match noise [default: 0.00]
80+
--nmoran NMORAN Moran Population Size, if Moran objective [default: 4]
81+
--plays PLAYS Number of recent plays in the lookup table [default: 2]
82+
--op_plays OP_PLAYS Number of recent plays in the lookup table [default: 2]
83+
--op_start_plays OP_START_PLAYS Number of opponent starting plays in the lookup table [default: 2]
7784
```
7885
7986
There are a number of options and you'll want to set the
@@ -87,17 +94,32 @@ so that there's enough variation introduced.
8794
$ python pso_evolve.py -h
8895
Particle Swarm strategy training code.
8996

97+
Original version by Georgios Koutsovoulos @GDKO :
98+
https://gist.github.com/GDKO/60c3d0fd423598f3c4e4
99+
Based on Martin Jones @mojones original LookerUp code
100+
90101
Usage:
91-
pso_evolve.py [-h] [-p PLAYS] [-s STARTING_PLAYS] [-g GENERATIONS]
92-
[-i PROCESSORS] [-o OPP_PLAYS] [-n NOISE]
102+
pso_evolve.py [-h] [--generations GENERATIONS] [--population POPULATION]
103+
[--mu MUTATION_RATE] [--bottleneck BOTTLENECK] [--processes PROCESSORS]
104+
[--output OUTPUT_FILE] [--objective OBJECTIVE] [--repetitions REPETITIONS]
105+
[--noise NOISE] [--nmoran NMORAN]
106+
[--plays PLAYS] [--op_plays OP_PLAYS] [--op_start_plays OP_START_PLAYS]
93107

94108
Options:
95-
-h --help show help
96-
-p PLAYS number of recent plays in the lookup table [default: 2]
97-
-o OPP_PLAYS number of recent opponent's plays in the lookup table [default: 2]
98-
-s STARTING_PLAYS number of opponent starting plays in the lookup table [default: 2]
99-
-i PROCESSORS number of processors to use [default: 1]
100-
-n NOISE match noise [default: 0.0]
109+
-h --help Show help
110+
--generations GENERATIONS Generations to run the EA [default: 500]
111+
--population POPULATION Starting population size [default: 10]
112+
--mu MUTATION_RATE Mutation rate [default: 0.1]
113+
--bottleneck BOTTLENECK Number of individuals to keep from each generation [default: 5]
114+
--processes PROCESSES Number of processes to use [default: 1]
115+
--output OUTPUT_FILE File to write data to [default: pso_tables.csv]
116+
--objective OBJECTIVE Objective function [default: score]
117+
--repetitions REPETITIONS Repetitions in objective [default: 100]
118+
--noise NOISE Match noise [default: 0.00]
119+
--nmoran NMORAN Moran Population Size, if Moran objective [default: 4]
120+
--plays PLAYS Number of recent plays in the lookup table [default: 2]
121+
--op_plays OP_PLAYS Number of recent plays in the lookup table [default: 2]
122+
--op_start_plays OP_START_PLAYS Number of opponent starting plays in the lookup table [default: 2]
101123
```
102124
103125
Note that to use the multiprocessor version you'll need to install pyswarm 0.70
@@ -107,46 +129,62 @@ directly (pip installs 0.60 which lacks mutiprocessing support).
107129
108130
```bash
109131
$ python ann_evolve.py -h
110-
Training ANN strategies with an evolutionary algorithm.
132+
ANN evolver.
133+
Trains ANN strategies with an evolutionary algorithm.
134+
135+
Original version by Martin Jones @mojones:
136+
https://gist.github.com/mojones/b809ba565c93feb8d44becc7b93e37c6
111137
112138
Usage:
113-
ann_evolve.py [-h] [-g GENERATIONS] [-u MUTATION_RATE] [-b BOTTLENECK]
114-
[-d MUTATION_DISTANCE] [-i PROCESSORS] [-o OUTPUT_FILE]
115-
[-k STARTING_POPULATION] [-n NOISE]
139+
ann_evolve.py [-h] [--generations GENERATIONS] [--population POPULATION]
140+
[--mu MUTATION_RATE] [--bottleneck BOTTLENECK] [--processes PROCESSORS]
141+
[--output OUTPUT_FILE] [--objective OBJECTIVE] [--repetitions REPETITIONS]
142+
[--noise NOISE] [--nmoran NMORAN]
143+
[--features FEATURES] [--hidden HIDDEN] [--mu_distance DISTANCE]
116144
117145
Options:
118-
-h --help show this
119-
-g GENERATIONS how many generations to run the program for [default: 10000]
120-
-u MUTATION_RATE mutation rate i.e. probability that a given value will flip [default: 0.4]
121-
-d MUTATION_DISTANCE amount of change a mutation will cause [default: 10]
122-
-b BOTTLENECK number of individuals to keep from each generation [default: 6]
123-
-i PROCESSORS number of processors to use [default: 4]
124-
-o OUTPUT_FILE file to write statistics to [default: weights.csv]
125-
-k STARTING_POPULATION starting population size for the simulation [default: 5]
126-
-n NOISE match noise [default: 0.0]
146+
-h --help Show help
147+
--generations GENERATIONS Generations to run the EA [default: 500]
148+
--population POPULATION Starting population size [default: 10]
149+
--mu MUTATION_RATE Mutation rate [default: 0.1]
150+
--bottleneck BOTTLENECK Number of individuals to keep from each generation [default: 5]
151+
--processes PROCESSES Number of processes to use [default: 1]
152+
--output OUTPUT_FILE File to write data to [default: ann_weights.csv]
153+
--objective OBJECTIVE Objective function [default: score]
154+
--repetitions REPETITIONS Repetitions in objective [default: 100]
155+
--noise NOISE Match noise [default: 0.00]
156+
--nmoran NMORAN Moran Population Size, if Moran objective [default: 4]
157+
--features FEATURES Number of ANN features [default: 17]
158+
--hidden HIDDEN Number of hidden nodes [default: 10]
159+
--mu_distance DISTANCE Delta max for weights updates [default: 5]
127160
```
128161
129162
### Finite State Machines
130163
131164
```bash
132165
$ python fsm_evolve.py -h
133-
FSM Evolve.
166+
Finite State Machine Evolver
134167
135168
Usage:
136-
fsm_evolve.py [-h] [-s NUM_STATES] [-g GENERATIONS]
137-
[-k STARTING_POPULATION] [-u MUTATION_RATE] [-b BOTTLENECK]
138-
[-i PROCESSORS] [-f OUTPUT_FILE] [-n NOISE]
169+
fsm_evolve.py [-h] [--generations GENERATIONS] [--population POPULATION]
170+
[--mu MUTATION_RATE] [--bottleneck BOTTLENECK] [--processes PROCESSORS]
171+
[--output OUTPUT_FILE] [--objective OBJECTIVE] [--repetitions REPETITIONS]
172+
[--noise NOISE] [--nmoran NMORAN]
173+
[--states NUM_STATES]
139174
140175
Options:
141-
-h --help show this
142-
-s NUM_STATES number FSM states [default: 16]
143-
-g GENERATIONS how many generations to run the program for [default: 500]
144-
-k STARTING_POPULATION starting population size for the simulation [default: 20]
145-
-u MUTATION_RATE mutation rate i.e. probability that a given value will flip [default: 0.1]
146-
-b BOTTLENECK number of individuals to keep from each generation [default: 10]
147-
-i PROCESSORS number of processors to use [default: 1]
148-
-f OUTPUT_FILE file to write data to [default: fsm_tables.csv]
149-
-n NOISE match noise [default: 0.00]
176+
-h --help Show help
177+
--generations GENERATIONS Generations to run the EA [default: 500]
178+
--population POPULATION Starting population size [default: 10]
179+
--mu MUTATION_RATE Mutation rate [default: 0.1]
180+
--bottleneck BOTTLENECK Number of individuals to keep from each generation [default: 5]
181+
--processes PROCESSES Number of processes to use [default: 1]
182+
--output OUTPUT_FILE File to write data to [default: fsm_tables.csv]
183+
--objective OBJECTIVE Objective function [default: score]
184+
--repetitions REPETITIONS Repetitions in objective [default: 100]
185+
--noise NOISE Match noise [default: 0.00]
186+
--nmoran NMORAN Moran Population Size, if Moran objective [default: 4]
187+
--states NUM_STATES Number of FSM states [default: 8]
150188
```
151189
152190
## Open questions

0 commit comments

Comments
 (0)