Difference between revisions of "AgentSmith"
m (→Strategy) |
|||
| (14 intermediate revisions by the same user not shown) | |||
| Line 1: | Line 1: | ||
| − | AgentSmith is | + | {{Navbox small |
| + | | title = Agent Smith Sub-pages | ||
| + | | parent = AgentSmith | ||
| + | | page1 = Version History | ||
| + | | page2 = Challenge Results | ||
| + | | page3 = Wolfmans Todo List | ||
| + | }} | ||
| + | |||
| + | 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 | {{Infobox Robot | ||
| Line 6: | Line 14: | ||
| caption = You hear that Mr. Anderson?... That is the sound of inevitability... It is the sound of your death... Goodbye, Mr. Anderson... | | caption = You hear that Mr. Anderson?... That is the sound of inevitability... It is the sound of your death... Goodbye, Mr. Anderson... | ||
| extends = [[AdvancedRobot]] | | extends = [[AdvancedRobot]] | ||
| − | | targeting = | + | | targeting = Virtual Guns with Linear, Circular and Head On Targeting |
| − | | movement = | + | | movement = [[DangerPrediction]] |
| current_version = 0.5 | | current_version = 0.5 | ||
| − | | download_link = - | + | | download_link = https://docs.google.com/uc?export=download&id=0B4FLgph-dzApWFBLclRLc09fMnM |
| isOpenSource = no | | isOpenSource = no | ||
| − | | isOneOnOne = | + | | isOneOnOne = yes |
}} | }} | ||
| Line 17: | 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. | 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 == | == Strategy == | ||
| Line 24: | Line 30: | ||
;How does it [[:Category:Movement|move]]? | ;How does it [[:Category:Movement|move]]? | ||
| − | + | 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]]? | ;How does it [[:Category:Targeting|fire]]? | ||
| − | + | 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]]? | ;How does it [[Dodging Bullets|dodge bullets]]? | ||
| − | + | See Movement above! | |
== Additional Information == | == Additional Information == | ||
| Line 40: | Line 46: | ||
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 == | |
| − | + | 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]] | ||
Latest revision as of 10:42, 8 December 2017
- Agent Smith Sub-pages:
- Version History - Challenge Results - Wolfmans Todo List
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.
| AgentSmith | |
 You hear that Mr. Anderson?... That is the sound of inevitability... It is the sound of your death... Goodbye, Mr. Anderson... | |
| Author(s) | Wolfman |
| Extends | AdvancedRobot |
| Targeting | Virtual Guns with Linear, Circular and Head On Targeting |
| Movement | DangerPrediction |
| Current Version | 0.5 |
| Download | |
Background Information
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
- How does it move?
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 fire?
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 dodge bullets?
See Movement above!
Additional Information
- Where did you get the name?
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 KD-Tree to do its Dynamic Clustering.
Thanks To
Everyone who contributes to the RoboWiki. It's an awesome resource, be proud of yourselves!
