Difference between revisions of "Raven"

From Robowiki
Jump to navigation Jump to search
(Restored edits authored by Dsekercioglu dated 2020-03-09T13:26:52+00:00)
 
(Give more info about the current state of Raven and remove the italics that make my eyes hurt)
Line 2: Line 2:
  
 
; Bot Name
 
; Bot Name
: ''Raven''
+
: Raven
  
 
; Author
 
; Author
: ''[[Dsekercioglu]]''
+
: [[Dsekercioglu]]
  
 
; Extends
 
; Extends
: ''[[AdvancedRobot]]''
+
: [[AdvancedRobot]]
  
 
; What's special about it?
 
; What's special about it?
: ''It is completely deterministic after the initialization.''
+
: Raven dynamically weights its movement classifiers using gradient-based optimization.
  
 
; Great, I want to try it. Where can I download it?
 
; Great, I want to try it. Where can I download it?
:''https://www.dropbox.com/s/2ydiomgfktzt4a5/dsekercioglu.mega.Raven_1.0.7.jar?dl=1''
+
: https://www.dropbox.com/s/ionjtk6rjk6pnyb/dsekercioglu.mega.Raven_2.9.jar?dl=1
 
 
  
 
; How competitive is it?
 
; How competitive is it?
: ''I don't know yet.''
+
: It's best is top 30
  
 
;Credits
 
;Credits
:''[[Skilgannon]] for the bugless, fast Kd-tree.''
+
:[[Skilgannon]] for the bugless, fast Kd-tree.
:''[[Cb]] for non iterative wall smoothing.''
+
:[[Cb]] for non-iterative wall smoothing.
:''[[Rozu]] for the precise prediction code.''
+
:[[Rozu]] for the precise prediction code.
:''[[Chase-san]] for the intercept method I used in my [[PPMEA]] calculations.''
+
:[[Chase-san]] for the intercept method I used in my [[PPMEA]] calculations.
:''[[AW]] for giving me the idea of using the integral of the danger function.''
+
:[[AW]] for giving me the idea of integrating the danger function in order to get the danger value for a given bot width.
 
== Strategy ==
 
== Strategy ==
  
 
; How does it [[Movement|move]]?
 
; How does it [[Movement|move]]?
: ''True Surfing''
+
: True Surfing.
  
 
; How does it fire?
 
; How does it fire?
: ''It uses [[GuessFactor]] with KNN''
+
: It uses [[GuessFactor]] with KNN.
  
 
; How does it [[Dodging Bullets|dodge bullets]]?
 
; How does it [[Dodging Bullets|dodge bullets]]?
: ''Tries to minimize the number of guess factors it gets hit by based on their weights and damage.''
+
: Tries to minimize the number of guess factors it gets hit by based on their weights and damage.
 
 
; How does the [[melee]] strategy differ from [[One-on-one]]  strategy?
 
: ''It doesn't support melee yet.''
 
 
 
; How does it select a target to attack/avoid in [[melee]]?
 
: ''It doesn't support melee yet.''
 
  
 
; What does it save between rounds and matches?
 
; What does it save between rounds and matches?
: ''Between rounds it saves the kd-trees. Between matches it doesn't save anything.''
+
: Between rounds it saves the kd-trees. Between matches it doesn't save anything.
  
 
== Additional Information ==
 
== Additional Information ==
  
 
; Where did you get the name?
 
; Where did you get the name?
: ''It just popped into my mind and I thought it would be a proper name for a bot with Machine Learning.''
+
: It just popped into my mind and I thought it would be a proper name for a bot with machine learning.
  
 
; Can I use your code?
 
; Can I use your code?
: ''Yes, I tried to make the code as clean and understandable as possible.''
+
: Yes, I tried to make the code as clean and understandable as possible.
  
 
; What's next for your robot?
 
; What's next for your robot?
: ''Better Bullet Shadow Calculations''
+
: Better Bullet Shadow Calculations.
: ''Tuning the guns since they haven't been tuned since the first version''
+
: Tuning the guns since they haven't been tuned since the first version.
: ''Gun Heat Waves''
+
: Gun Heat Waves.
: ''Precise MEA for movement''
+
: Maybe a pre-trained movement or gun to use in the first ticks of the battle.
: ''Maybe a pre-trained movement or gun to use in the first ticks of the battle''
+
: Add a flattener that actually improves its scores against adaptive targeting.
: ''Succeed at not forgetting to put protection against Bullet Shielders in the next version''
 
  
 
; Does it have any [[White Whale]]s?
 
; Does it have any [[White Whale]]s?
: ''Bullet Shielders but that issue should be solved soon.''
+
: Drifter seems to have the highest KNNPBI.
  
 
; What other robot(s) is it based on?
 
; What other robot(s) is it based on?
: ''It's kind of based on WhiteFang, I have tried to copy the design but make it as precise as it can be.''
+
: It's kind of based on WhiteFang, I have tried to copy the design but make it as precise as it can be.
  
 
[[Category:Templates|Bots]]
 
[[Category:Templates|Bots]]

Revision as of 00:41, 18 July 2020

Background Information

Bot Name
Raven
Author
Dsekercioglu
Extends
AdvancedRobot
What's special about it?
Raven dynamically weights its movement classifiers using gradient-based optimization.
Great, I want to try it. Where can I download it?
https://www.dropbox.com/s/ionjtk6rjk6pnyb/dsekercioglu.mega.Raven_2.9.jar?dl=1
How competitive is it?
It's best is top 30
Credits
Skilgannon for the bugless, fast Kd-tree.
Cb for non-iterative wall smoothing.
Rozu for the precise prediction code.
Chase-san for the intercept method I used in my PPMEA calculations.
AW for giving me the idea of integrating the danger function in order to get the danger value for a given bot width.

Strategy

How does it move?
True Surfing.
How does it fire?
It uses GuessFactor with KNN.
How does it dodge bullets?
Tries to minimize the number of guess factors it gets hit by based on their weights and damage.
What does it save between rounds and matches?
Between rounds it saves the kd-trees. Between matches it doesn't save anything.

Additional Information

Where did you get the name?
It just popped into my mind and I thought it would be a proper name for a bot with machine learning.
Can I use your code?
Yes, I tried to make the code as clean and understandable as possible.
What's next for your robot?
Better Bullet Shadow Calculations.
Tuning the guns since they haven't been tuned since the first version.
Gun Heat Waves.
Maybe a pre-trained movement or gun to use in the first ticks of the battle.
Add a flattener that actually improves its scores against adaptive targeting.
Does it have any White Whales?
Drifter seems to have the highest KNNPBI.
What other robot(s) is it based on?
It's kind of based on WhiteFang, I have tried to copy the design but make it as precise as it can be.