Gaff - Revision history

MultiplyByZer0: Fix broken link and update

2017-08-12T23:24:24Z

Fix broken link and update

Darkcanuck: Undo revision 14420 by AmandaBaker (Talk)

2010-01-11T14:45:58Z

Undo revision 14420 by AmandaBaker (Talk)

AmandaBaker at 14:36, 11 January 2010

2010-01-11T14:36:05Z

Darkcanuck: link to targeting page

2009-07-16T18:21:18Z

link to targeting page

Darkcanuck: updates, credits

2009-05-12T06:45:03Z

updates, credits

Darkcanuck: migrated page from old wiki

2009-04-30T06:43:03Z

migrated page from old wiki

New page

{{Infobox Robot
| name = Gaff
| author = [[Darkcanuck]]
| extends = [[AdvancedRobot]]
| targeting = [[Neural Targeting]] (GF)
| movement = [[Random Movement]]
| released = June 2008
| rating = 1759 (93rd)
| current_version = 1.30
| license = closed
| download_link = http://jeromelavigne.ca/robocode/darkcanuck.Gaff_1.30.jar
| isOneOnOne = true
| isMelee = false
| isOpenSource = false
}}

== Sub-Pages ==
[[/VersionHistory | Version History]]

== Background Information ==

; What's special about it?
I got tired of wrestling with learning bots and made Gaff using a simple movement that popped into my head. This bot was originally a testbed for a new targeting method I was working on.

But Gaff's claim to fame is achieving the highest score vs. [[Shadow]] in the [[Targeting_Challenge_2K7/FastLearningResults|fast learning Targeting Challenge 2K7]] by a wide margin.

; How competitive is it?
Currently in the top-100 of the 1-on-1 [[RoboRumble]].

== Strategy ==

; How does it [[Movement|move]]?
Gaff was originally based on a cornering movement which tried to push enemies into the corners to narrow their escape angle and expose near-wall profile flaws. But since version 1.10, Gaff uses a multi-mode movement, consisting of:
* the basic cornering movement
* a simple orbital-style movement with bullet avoidance
* a random orbital-style movement which attempts to put Gaff at a random GF every time the opponent fires.

The cornering and simple orbital movement have a bit of randomness mixed in, plus the bullet prediction/dodging code from [[Leon]]. The random orbit makes no attempt to predict or dodge.

; How does it fire?
Uses a single neural-network with <strike>one hidden layer</strike> no hidden layers. The code still assumes a virtual gun array and is nicely pluggable so that I can test different combinations if I feel the need to go back to multiple guns.

; How does the [[melee]] strategy differ from [[One-on-one]] strategy?
No difference, but the movement algorithm doesn't take more than one opponent into account so melee performance could be pretty bad.

; How does it select a target to attack/avoid in [[melee]]?
Selects the closest target, with some protection against target thrashing.

; What does it save between rounds and matches?
Between rounds, saves all neural network weights, targeting stats and bullet dodging data.
Nothing saved between matches.

== Additional Information ==

; Where did you get the name?
Blade Runner again.

; Can I use your code?
Not yet. But feel free to ask if you're curious and maybe I'll post some snippets

; What's next for your robot?
* <strike>Improve the NN targeting</strike> DONE
* Add a melee strategy, since I prefer that field over 1on1
* Improve targeting against random movers
* Make the multi-mode movement sophisticated enough to secure a top-50 position

; Does it have any [[White Whale]]s?
* [[CassiusClay]] is proving frustratingly difficult to hit in the [[Targeting Challenge 2K7]]
* [[DogManSPE]] is Gaff's worst ProblemBot, followed by [[Infinity]]

; What other robot(s) is it based on?
Most of the framework is shared with [[Leon]].
Targeting inspired by [[Engineer]], inputs to the targeting networks originally based on [[Raiko]]'s segmentation but heavily refined since then.

__NOTOC__ __NOEDITSECTION__
[[Category:MegaBots]]

← Older revision		Revision as of 14:45, 11 January 2010
Line 79:		Line 79:

	Inputs to the targeting network was originally based on [[Raiko]]'s segmentation but heavily refined since then. The current versions use a data arrangement heavily inspired by [[DrussGT]], which was graciously shared by [[Skilgannon]] on the [[TC2K7]] chat page. The new data also uses a modified version of [[Simonton]]'s radial-distance-to-wall algorithm.		Inputs to the targeting network was originally based on [[Raiko]]'s segmentation but heavily refined since then. The current versions use a data arrangement heavily inspired by [[DrussGT]], which was graciously shared by [[Skilgannon]] on the [[TC2K7]] chat page. The new data also uses a modified version of [[Simonton]]'s radial-distance-to-wall algorithm.
−	This topic is all about [http://www.besttermpaper.com essay papers]. In this topic you can see some of tips and guidelines on how to be an effective writer in research paper. If you are interested in this topic just click the link for more details and information or reply to this message.

	Also thanks to [[Rednaxela]] for inspiring the training approach used in Gaff's anti-surfer gun.		Also thanks to [[Rednaxela]] for inspiring the training approach used in Gaff's anti-surfer gun.

← Older revision		Revision as of 14:36, 11 January 2010
Line 79:		Line 79:

	Inputs to the targeting network was originally based on [[Raiko]]'s segmentation but heavily refined since then. The current versions use a data arrangement heavily inspired by [[DrussGT]], which was graciously shared by [[Skilgannon]] on the [[TC2K7]] chat page. The new data also uses a modified version of [[Simonton]]'s radial-distance-to-wall algorithm.		Inputs to the targeting network was originally based on [[Raiko]]'s segmentation but heavily refined since then. The current versions use a data arrangement heavily inspired by [[DrussGT]], which was graciously shared by [[Skilgannon]] on the [[TC2K7]] chat page. The new data also uses a modified version of [[Simonton]]'s radial-distance-to-wall algorithm.
		+	This topic is all about [http://www.besttermpaper.com essay papers]. In this topic you can see some of tips and guidelines on how to be an effective writer in research paper. If you are interested in this topic just click the link for more details and information or reply to this message.

	Also thanks to [[Rednaxela]] for inspiring the training approach used in Gaff's anti-surfer gun.		Also thanks to [[Rednaxela]] for inspiring the training approach used in Gaff's anti-surfer gun.

@@ Line 16: / Line 16: @@
 '''Sub-Pages:'''
-[[/VersionHistory | Version History]] | [[/Challenges | Challenges]]
+[[/VersionHistory | Version History]] | [[/Challenges | Challenges]] | [[/Targeting | Targeting]]
 == Background Information ==
@@ Line 40: / Line 40: @@
 ; How does it fire?
-Uses a single neural-network with <strike>one hidden layer</strike> no hidden layers.  The code still assumes a virtual gun array and is nicely pluggable so that I can test different combinations if I feel the need to go back to multiple guns.
+All the gory details are here:  [[Gaff/Targeting]]
 ; How does the [[melee]] strategy differ from [[One-on-one]]  strategy?

@@ Line 7: / Line 7: @@
 | released        = June 2008
 | rating          = 1689 (95th)
-| current_version = 1.32rm
+| current_version = 1.50
 | license         = closed
-| download_link   = http://jeromelavigne.ca/robocode/darkcanuck.Gaff_1.30.jar
+| download_link   = http://robocode-archive.strangeautomata.com/robots/darkcanuck.Gaff_1.50.jar
 | isOneOnOne      = true
 | isMelee         = false
@@ Line 23: / Line 23: @@
 I got tired of wrestling with learning bots and made Gaff using a simple movement that popped into my head.  This bot was originally a testbed for a new targeting method I was working on.
-But Gaff's claim to fame is achieving the highest score vs. [[Shadow]] in the [[Targeting_Challenge_2K7/FastLearningResults|fast learning Targeting Challenge 2K7]] by a wide margin.
+But Gaff's claim to fame is achieving the highest score vs. [[Shadow]] in the [[Targeting Challenge 2K7/Fast Learning Results|fast learning Targeting Challenge 2K7]] by a wide margin.
 ; How competitive is it?
-Currently in the top-100 of the 1-on-1 [[RoboRumble]].
+Currently in the top-60 of the 1-on-1 [[RoboRumble]].
 == Strategy ==
@@ Line 51: / Line 50: @@
 Between rounds, saves all neural network weights, targeting stats and bullet dodging data.
 Nothing saved between matches.
 == Additional Information ==
@@ Line 73: / Line 71: @@
 ; What other robot(s) is it based on?
 Most of the framework is shared with [[Leon]].
 == Credits ==