Machine Learning Recruiter - Revision history

Soliton at 15:54, 25 October 2019

2019-10-25T15:54:46Z

2012-12-08T15:19:26Z

Add AI category

2012-11-23T03:52:46Z

‎Win percentages for different AI Pairs: Remove result for Ron, since expected release did not occur in time and Ron has since changed

2012-11-14T00:56:38Z

‎Win percentages for different AI Pairs: Add result when Arcanclave Citadel is not included

2012-11-14T00:46:39Z

‎Win percentages for different AI Pairs: Add results for ML Recruiter 0.3 vs latest Ron recruit to illustrate importance of recruit location

2012-11-12T08:02:57Z

‎ML Recruiter development roadmap

2012-10-29T01:57:55Z

‎Win percentages for different AI Pairs: Add version of Ron recruiter

2012-10-29T01:42:59Z

‎How to train your own ML Recruiter

2012-10-29T01:35:15Z

‎Bugs

2012-10-29T01:26:40Z

‎ML Recruiter development roadmap

← Older revision		Revision as of 15:19, 8 December 2012
Line 463:		Line 463:
	** Add missing special abilities (plague, leadership, and unit upkeep)		** Add missing special abilities (plague, leadership, and unit upkeep)
	** Add 95% confidence intervals to the win ratios in analyze_log.py and add measures of entropy (randomness) to analyze_recruitment.py. Entropy is a good measure of the variety of units that a recruiter is recruiting--for game play, more is better.		** Add 95% confidence intervals to the win ratios in analyze_log.py and add measures of entropy (randomness) to analyze_recruitment.py. Entropy is a good measure of the variety of units that a recruiter is recruiting--for game play, more is better.
		+
		+	[[Category:AI]]

@@ Line 84: / Line 84: @@
 |54.1%
 |Ron Recruit is the recruiter build into [http://forums.wesnoth.org/viewtopic.php?f=10&t=34976&start=405 AI Demos]
 |-
 |ML Recruiter 0.3 (Recommended)

@@ Line 89: / Line 89: @@
 |1355
 |41.8%
-|Maps such as Arcanclave Citadel show that recruit location is a significant factor in success.
+|Maps such as Arcanclave Citadel show that recruit location is a significant factor in success. If the games on Arcanclave Citadel are not included, the ML recruiter wins 45.1% of the games.
 |-
 |ML Recruiter 0.3 (Recommended)

@@ Line 84: / Line 84: @@
 |54.1%
 |Ron Recruit is the recruiter build into [http://forums.wesnoth.org/viewtopic.php?f=10&t=34976&start=405 AI Demos]
 |-
 |ML Recruiter 0.3 (Recommended)

@@ Line 452: / Line 452: @@
 ** New script (run_model_and_make_new_model.py) for running games and building a new neural net based on the data gathered from those games
 ** Improved performance:  Defeats ML Recruiter 0.2 58% of the time
-* ML Recruiter 0.3.1 (planned):
+* ML Recruiter 0.4 (11/11/2012):
-** Run on all 2-player maps (except maybe Dark Forecast, which seems to have a custom recruiter)
+** Run on all 2-player maps (except Dark Forecast, which has a custom recruiter)
 ** Refactor code to separate features from predicted values
-** Add 95% confidence intervals to the win ratios in analyze_log.py and add measures of entropy (randomness) to analyze_recruitment.py.  Entropy is a good measure of the variety of units that a recruiter is recruiting--for game play, more is better.
+** Added timeout option to ai_test2.py.  Also report time statistics in analyze_log.py
-* ML Recruiter 0.4 (planned)
+** Improved recruiter for the Ron recruiter.  It still underperforms the Ron recruiter on most maps when used with the other Ron CA's, though.
 ** Run on all mainline multiplayer maps
 ** Experiment with using as the [http://forums.wesnoth.org/viewtopic.php?f=10&t=34976 AI-Demos] recruiter
 ** Add missing special abilities (plague, leadership, and unit upkeep)

@@ Line 80: / Line 80: @@
 |-
 |ML Recruiter 0.3
-|Ron Recruiter
+|Ron Recruiter 0.11.4
 |1186
 |54.1%

← Older revision		Revision as of 01:42, 29 October 2012
Line 422:		Line 422:

	=How to train your own ML Recruiter=		=How to train your own ML Recruiter=
		+	utils/ai_test/run_model_and_make_new_model.py is an end-to-end script for running a whole bunch of training games of Wesnoth and then training a new model based on the data output by that run. Documentation on this script can be seen by running
		+	run_model_and_make_new_model.py --help
		+	Note that this script assumes that [http://waffles.sourceforge.net/ the Waffles machine learning toolkit] is installed and that waffles/bin/ is in your path.

	=Known issues=		=Known issues=

@@ Line 426: / Line 426: @@
 ==Bugs==
 # Haven't added new Waffles files to Visual C++, so it won't compile under VC++.  I need some help with this.
-# The default for multiplayer games is that units require only 70% of normal experience to promote, however when a game is run from the command line, it always requires normal 100% of experience to promote.  Consequently MLR doesn't see units promote as much as they should in training, which would slightly distort its training data.
+# The default for multiplayer games is that units require only 70% of normal experience to promote, however when a game is run from the command line, it always requires normal 100% of experience to promote.  Consequently MLR doesn't see units promote as much as they should in training, which would slightly distort its training data.  This is a [https://gna.org/bugs/?19895 limitation of Wesnoth], not MLR.
 ==Current Limitations==