BeepBoop - Revision history

Kev: update BeepBoop's page

2024-01-09T21:28:50Z

update BeepBoop's page

Kev: Add some more credits

2021-06-08T00:42:06Z

Add some more credits

Kev: link to understanding page

2021-05-24T00:56:51Z

link to understanding page

Kev: new page for BeepBoop

2021-05-18T22:55:44Z

new page for BeepBoop

New page

{{Navbox small
| title = Sub-pages
| page1 = Version History
}}
{{Infobox Robot
| author = [[User:Kev|Kev]]
| extends = [[AdvancedRobot]]
| targeting = [[GuessFactor Targeting|GuessFactor Targeting]]
| movement = [[Wave Surfing|Wave Surfing]]
| current_version = 0.1
| license = [[RWPCL]]
| download_link = https://drive.google.com/uc?export=download&id=1ElDPSPl7QZofjrA-PrMOfTH2TQo8Dmdo
| isOpenSource = yes
| isOneOnOne = yes
}}

== Background Information ==

; What's special about it?

It is my first new bot in over 10 years!

; How competitive is it?

We'll see! It does really well against top bots, but I'm less sure how it will fare against the general rumble population.

== Strategy ==

; How does it [[Movement|move]]?

It uses a new type of [[WaveSurfing]] I call PathSurfing. It is a sort of generalization of [[Wave Surfing/True Surfing|True Surfing]]. As well as considering going forward/backward/stopping until the wave passes, it also considers other "paths"; for example one might be driving forward 3 ticks and then reversing 5 ticks. An advantage over [[Wave Surfing/Go To|GoTo Surfing]] is that it considers ''how'' it gets to a point as well as the point itself. For example, it sometimes drives past and then reverses into the lowest danger point if that helps is get to a low-danger area on the next wave. The danger computation combines [[Bullet Shadows]] with multiple [[KNN]] systems including [[Flattener]]s.

; How does it fire?

It uses two [[KNN]]/[[GuessFactor]] guns, one tuned to hit surfers and the other tuned to hit other bots. The formulas for the gun and movement are learned offline using [https://www.tensorflow.org TensorFlow]. For [[Energy Management]], it tries to directly maximize the expected score at the end of the round by predicting its win probability and expected bullet damage for various candidate bullet powers.

; How does the [[Melee|melee]] strategy differ from [[One on One|one-on-one]] strategy?

It currently can't fight in melees.

; What does it save between rounds and matches?

Gun/movement data between rounds, nothing between matches.

== Additional Information ==

; Where did you get the name?

It's just a silly name for a robot!

; Can I use your code?

Yes, but please (1) give credit and (2) open-source your bot!

; What's next for your robot?

Add bullet shielding? I think it's a bit of a cheap trick, but it might be necessary for getting competitive with [[DrussGT]] in terms of APS.

; What other robot(s) is it based on?

I used many ideas from throughout the wiki.
* It started off based on [[WaveSerpent]], although at this point it works quite differently.
* It uses [[Wall Smoothing/Implementations/Non-Iterative|non-iterative WallSmoothing]] by [[David Alves]] and [[Wall_Smoothing/Implementations/Fancy_Stick|fancy-stick WallSmoothing]] by [[Simonton]]
* It uses precise wave intersection utilities and anti-basic-surfer bullet powers from [[DrussGT]].
* It uses [[Rednaxela]]'s [[User:Rednaxela/kD-Tree|kd-tree]] implementation.
* It was indirectly influenced by many other bots/pages including [[Diamond]], [[CassiusClay]], [[ScalarR]], [[Kawigi]]'s [[GuessFactor Targeting Tutorial]], and [[Maximum_Escape_Angle/Precise_Positional/Non-Iterative|non-iterative PPMEA]].

[[Category:MegaBots]]

@@ Line 24: / Line 24: @@
 ; How competitive is it?
-We'll see! It does really well against top bots, but I'm less sure how it will fare against the general rumble population.
+It is the current robobumble [[RoboRumble/Kings|King]].
 == Strategy ==
@@ Line 34: / Line 34: @@
 ; How does it fire?
-It uses two [[KNN]]/[[GuessFactor]] guns, one tuned to hit surfers and the other tuned to hit other bots. The formulas for the gun and movement are learned offline using [https://www.tensorflow.org TensorFlow]. For [[Energy Management]], it tries to directly maximize the expected score at the end of the round by predicting its win probability and expected bullet damage for various candidate bullet powers.
+It uses two [[KNN]]/[[GuessFactor]] guns, one tuned to hit surfers and the other tuned to hit other bots. The embedding functions for the gun and movement are learned offline using gradient descent. As well as trying to hit the opponent, it also tries to create helpful [[Bullet_Shadow|bullet shadows]] that shield its movement. For [[Energy Management]], it aims to directly maximize the expected score at the end of the round by predicting its win probability and expected bullet damage for various candidate bullet powers.
 ; What does it save between rounds and matches?
-Gun/movement data between rounds, nothing between matches.
+Aiming/movement data between rounds, nothing between matches.
 == Additional Information ==
@@ Line 53: / Line 49: @@
 Yes, but please (1) give credit and (2) open-source your bot!
 ; What other robot(s) is it based on?

@@ Line 62: / Line 62: @@
 I used many ideas from throughout the wiki.
 * It started off based on [[WaveSerpent]], although at this point it works quite differently.
 * It uses [[Wall Smoothing/Implementations/Non-Iterative|non-iterative WallSmoothing]] by [[David Alves]] and [[Wall_Smoothing/Implementations/Fancy_Stick|fancy-stick WallSmoothing]] by [[Simonton]]
-* It uses precise wave intersection utilities and anti-basic-surfer bullet powers from [[DrussGT]].
+* It was indirectly influenced by many other bots/pages including [[CassiusClay]], [[ScalarR]], [[Kawigi]]'s [[GuessFactor Targeting Tutorial]], [[Maximum_Escape_Angle/Precise_Positional/Non-Iterative|non-iterative PPMEA]], and [[Innovations since 2005]].
 [[Category:MegaBots]]

@@ Line 2: / Line 2: @@
 | title        = Sub-pages
 | page1        = Version History
 }}
 {{Infobox Robot