Revision as of 04:49, 24 August 2017 by MultiplyByZer0
|Targeting||Neural Targeting with GuessFactors|
- What's special about it?
- It's mine and it's the first bot to use self-organizing maps for gunnery and movement.
- How competitive is it?
- It is rather competitive, currently ranked 39th in RoboRumble 1v1.
- How does it fire?
- Again it uses an SOM to store/analyze statistics on the enemy's movement.
- How does the melee strategy differ from one-on-one strategy?
- There is no melee strategy. See EngineerMelee.
- How does it select a target to attack/avoid in melee?
- I guess it would attack the first bot it saw, obliviously believing it was in one on one.
- What does it save between rounds and matches?
- It saves its neural nets between rounds, nothing between matches.
- Where did you get the name?
- It seemed appropriate for a learning bot.
- Can I use your code?
- What's next for your robot?
- Be as good as PowerHouse.
- Does it have any White Whales?
- The gun is still pretty weak against Wave Surfers, but there is a lot of room for improvement still...
- What other robot(s) is it based on?
It's basically PowerHouse's core structure with SOM neural networks in place of PH's more "traditional" array based intelligence gathering.
- Not so anymore. As of version 0.2.3 I have redesigned and rewritten just about everything that was inherited from PowerHouse.