AgentSmith - Revision history

Wolfman at 09:42, 8 December 2017

2017-12-08T09:42:35Z

Wolfman at 07:48, 23 July 2015

2015-07-23T07:48:31Z

Wolfman at 07:44, 23 July 2015

2015-07-23T07:44:46Z

Wolfman at 18:41, 28 November 2013

2013-11-28T18:41:56Z

Wolfman: /* TC2K7 Results */

2013-11-26T22:21:48Z

TC2K7 Results

Wolfman at 22:10, 26 November 2013

2013-11-26T22:10:09Z

Wolfman at 16:26, 18 March 2013

2013-03-18T16:26:03Z

Wolfman at 16:06, 18 March 2013

2013-03-18T16:06:05Z

Wolfman: /* TC2K7 Results */

2013-03-18T12:14:09Z

TC2K7 Results

Wolfman: /* TC2K7 Results */

2013-03-18T12:04:44Z

TC2K7 Results

@@ Line 7: / Line 7: @@
 }}
-AgentSmith is currently a work in progress bot designed for the 1v1 rumble competition.
+AgentSmith is a bot designed just for the 1v1 rumble competition. It is being replaced by [[AgentSmithRedux]]. Its currently the highest ranked bot from the UK, and at its peak was inside the top 50 bots, but has since been pushed out of the top 50 by newer bots.
 {{Infobox Robot
@@ Line 16: / Line 16: @@
 | targeting       = Virtual Guns with Linear, Circular and Head On Targeting
 | movement        = [[DangerPrediction]]
-| current_version = 0.1
+| current_version = 0.5
 | download_link   = https://docs.google.com/uc?export=download&id=0B4FLgph-dzApWFBLclRLc09fMnM
 | isOpenSource    = no
@@ Line 25: / Line 25: @@
 AgentSmith has been a bot name I have used for a couple of bots that I have never released over the years. They have always had one thing in common: They used machine learning techniques to try to improve their score. I have used both reinforcement learning and genetic algorithms in various guises. However the bots have never been terribly competitive because the base movement and targeting techniques implemented were never up to scratch and trying to improve the parameters of rubbish techniques doesn't improve the technique, only the effectiveness of the technique.
 == Strategy ==
@@ Line 32: / Line 30: @@
 ;How does it [[:Category:Movement|move]]?
-I've recently implemented a new technique I've currently called [[DangerPrediction]]. Its still in development so I'm not going to write too much about it but it doesn't surf any waves. It generates possible routes it could take, evaluates danger along those routes and chooses the route with the least danger. Its currently 99% effective versus most linear, circular and head on targeting strategies such as the Wave Surfing challenge bots, but it falls down at the moment versus Guess Factor, DC and pattern matching guns.
+I've implemented a new technique I've currently called [[DangerPrediction]]. Its still in development so I'm not going to write too much about it but it doesn't surf any waves. It generates possible routes it could take, evaluates danger along those routes and chooses the route with the least danger. Its currently 99% effective versus most linear, circular and head on targeting strategies such as the Wave Surfing challenge bots, but it falls down at the moment versus Guess Factor, DC and pattern matching guns.
 ;How does it [[:Category:Targeting|fire]]?
-I've just got a simple Virtual Gun array at the moment choosing the best gun between various guns including Linear, Circular and Head On and now with a DC gun.
+Its just got a simple Virtual Gun array at the moment choosing the best gun between various guns including Linear, Circular and Head On and now with a DC gun.
 ;How does it [[Dodging Bullets|dodge bullets]]?

@@ Line 33: / Line 33: @@
 I've recently implemented a new technique I've currently called [[DangerPrediction]]. Its still in development so I'm not going to write too much about it but it doesn't surf any waves. It generates possible routes it could take, evaluates danger along those routes and chooses the route with the least danger. Its currently 99% effective versus most linear, circular and head on targeting strategies such as the Wave Surfing challenge bots, but it falls down at the moment versus Guess Factor, DC and pattern matching guns.
 ;How does it [[:Category:Targeting|fire]]?
-I've just got a simple Virtual Gun array at the moment choosing the best gun between Linear, Circular and Head On targeting. Nothing special at the moment but plan on adding GF and DC guns to the array.
+I've just got a simple Virtual Gun array at the moment choosing the best gun between various guns including Linear, Circular and Head On and now with a DC gun.
 ;How does it [[Dodging Bullets|dodge bullets]]?

← Older revision		Revision as of 07:44, 23 July 2015
Line 49:		Line 49:

	Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,		Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,
		+
		+	== Credits ==
		+
		+	Agent Smith now uses Skilgannon's [[User:Skilgannon/KDTree\|KD-Tree]] to do its Dynamic Clustering.

	== Thanks To ==		== Thanks To ==

← Older revision		Revision as of 18:41, 28 November 2013
Line 50:		Line 50:
	Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,		Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,

		+	== Thanks To ==

		+	Everyone who contributes to the RoboWiki. It's an awesome resource, be proud of yourselves!

	[[Category:1-vs-1_Bots\|AgentSmith]]		[[Category:1-vs-1_Bots\|AgentSmith]]

← Older revision		Revision as of 22:21, 26 November 2013
Line 50:		Line 50:
	Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,		Agent Smith from the Matrix trilogy, a program that is relentless but can only learn within the bounds of its programming,

−	~~== TC2K7 Results ==~~

−	~~I'm going to keep track of my TC2K7 results as a guide to see how my gun is improving over the different versions:~~
−
−	~~{\| border="1"~~
−	~~\|'''Version'''~~
−	~~\|'''CC'''~~
−	~~\|'''RMX'''~~
−	~~\|'''SHA'''~~
−	~~\|'''WS'''~~
−	~~\|'''WOE'''~~
−	~~\|'''DM'''~~
−	~~\|'''FT'''~~
−	~~\|'''GG'''~~
−	~~\|'''RMC'''~~
−	~~\|'''WLO'''~~
−	~~\|'''TOTAL'''~~
−	~~\|'''Comments'''~~
−	\|-
−	~~\| 0.1~~
−	~~\|69.60~~
−	~~\|72.48~~
−	~~\|71.34~~
−	~~\|78.64~~
−	~~\|70.86~~
−	~~\|90.12~~
−	~~\|81.35~~
−	~~\|88.53~~
−	~~\|81.72~~
−	~~\|83.81~~
−	~~\|78.85~~
−	~~\|1 season~~
−	\|}

	[[Category:1-vs-1_Bots\|AgentSmith]]		[[Category:1-vs-1_Bots\|AgentSmith]]

@@ Line 14: / Line 14: @@
 | caption         = You hear that Mr. Anderson?... That is the sound of inevitability... It is the sound of your death... Goodbye, Mr. Anderson...
 | extends         = [[AdvancedRobot]]
-| targeting       = [[Dynamic Clustering]]
+| targeting       = Virtual Guns with Linear, Circular and Head On Targeting
-| movement        = None yet
+| movement        = [[DangerPrediction]]
-| current_version = 0.5
+| current_version = 0.1
-| download_link   = -na-
+| download_link   = https://docs.google.com/uc?export=download&id=0B4FLgph-dzApWFBLclRLc09fMnM
 | isOpenSource    = no
-| isOneOnOne      = no
+| isOneOnOne      = yes
 }}
@@ Line 32: / Line 32: @@
 ;How does it [[:Category:Movement|move]]?
-Movement has not yet been implemented as I am currently focusing on targeting.
+I've recently implemented a new technique I've currently called [[DangerPrediction]]. Its still in development so I'm not going to write too much about it but it doesn't surf any waves. It generates possible routes it could take, evaluates danger along those routes and chooses the route with the least danger. Its currently 99% effective versus most linear, circular and head on targeting strategies such as the Wave Surfing challenge bots, but it falls down at the moment versus Guess Factor, DC and pattern matching guns.
 ;How does it [[:Category:Targeting|fire]]?
-[[DynamicClustering]]. However I aim for my version to be a tiny bit different - its [[DynamicClustering]] with automatic segmentation weighting at run time.
+I've just got a simple Virtual Gun array at the moment choosing the best gun between Linear, Circular and Head On targeting. Nothing special at the moment but plan on adding GF and DC guns to the array.
 ;How does it [[Dodging Bullets|dodge bullets]]?
-It doesn't yet.
+See Movement above!
 == Additional Information ==

@@ Line 3: / Line 3: @@
 | parent = AgentSmith
 | page1 = Version History
-| page2 = Wolfmans Todo List
+| page2 = Challenge Results
 }}

← Older revision		Revision as of 16:06, 18 March 2013
Line 1:		Line 1:
		+	{{Navbox small
		+	\| title = Agent Smith Sub-pages
		+	\| parent = AgentSmith
		+	\| page1 = Version History
		+	\| page2 = Wolfmans Todo List
		+	}}
		+
	AgentSmith is currently a work in progress bot designed for the 1v1 rumble competition.		AgentSmith is currently a work in progress bot designed for the 1v1 rumble competition.

@@ Line 65: / Line 65: @@
 |78.64
 |70.86
-|90.124
+|90.12
 |81.35
 |88.53
 |81.72
-|0
+|83.81
-|0
+|78.85
 |1 season
 |}
 [[Category:1-vs-1_Bots|AgentSmith]]

@@ Line 67: / Line 67: @@
 |90.124
 |81.35
-|0
+|88.53
 |81.72
 |0