Difference between revisions of "User:Tkiesel/Dev Notebook"
Jump to navigation
Jump to search
(New sub-project!) |
m (reordering, details) |
||
| Line 4: | Line 4: | ||
#* <span style="text-decoration: line-through;">Dilemma - Roll my own or utilize someone else's?</span> | #* <span style="text-decoration: line-through;">Dilemma - Roll my own or utilize someone else's?</span> | ||
#* see [[User:Tkiesel/MovementPredictor]] | #* see [[User:Tkiesel/MovementPredictor]] | ||
| + | # Implement Wave Surfing | ||
| + | #* Farewell Aristocles. You were a faithful friend, if a bit dodgy during round 1. ;) | ||
| + | #* GoTo is what DeBroglie used to have, but TrueSurfing seems more philosophically satisfying at the moment... | ||
| + | #* Danger function to include a term for field position? Corners are bad after all, and a slightly increased hit risk might be worth it to get out of a corner. | ||
| + | #* Eventually, the pluggable EndPredictionCondition interface in MovementPredictor should make surfing multiple waves easier.. and allow me to handle cases like the following via a discrete Class that can handle the details: | ||
| + | #** Wave A and Wave B are coming toward you. If you orbit clockwise or stop, Wave A will hit first. Remove Wave A and predict-surf remaining waves. If you orbit counter-clockwise, wave B will hit you first. Remove Wave B and predict-surf remaining waves | ||
# Get a small Virtual Gun array going. Main GF gun, anti-adaptive GF gun, circular targeter, dead-stop targeter. For kicks. ;) | # Get a small Virtual Gun array going. Main GF gun, anti-adaptive GF gun, circular targeter, dead-stop targeter. For kicks. ;) | ||
#* Weight points in anti-adaptive gun via half-life based on round number. | #* Weight points in anti-adaptive gun via half-life based on round number. | ||
| Line 9: | Line 15: | ||
#* Test choosing gun via history of this shot (the k-nearest-neighbors can report which gun did best on them) vs. general history of the match.. Probably lots of trade-offs here. | #* Test choosing gun via history of this shot (the k-nearest-neighbors can report which gun did best on them) vs. general history of the match.. Probably lots of trade-offs here. | ||
# Bullet Shadows (fairly easy with the Universe/Bot structure) | # Bullet Shadows (fairly easy with the Universe/Bot structure) | ||
| − | |||
| − | |||
| − | |||
| − | |||
# Debug and Evaluate how the bot works in the Rumble without extensive tuning. | # Debug and Evaluate how the bot works in the Rumble without extensive tuning. | ||
| − | # Download and get [[RoboResearch]] working. | + | # <span style="text-decoration: line-through;">Download and get [[RoboResearch]] working.</span> |
#* Code a version of Debroglie to read/write dimension weights and real/virtual wave weighting from a .txt file. Let it chew on the [[Targeting Challenge RM]] bots for a week or two to explore the solution space. | #* Code a version of Debroglie to read/write dimension weights and real/virtual wave weighting from a .txt file. Let it chew on the [[Targeting Challenge RM]] bots for a week or two to explore the solution space. | ||
#* Pick the few best local maxima, do some runs that explore the space near them. | #* Pick the few best local maxima, do some runs that explore the space near them. | ||
#* Repeat all of this for the anti-adaptive gun with some relevant bots. | #* Repeat all of this for the anti-adaptive gun with some relevant bots. | ||
#* Repeat with movement weights using [[Movement Challenge 2K7|MC2K7]], etc. | #* Repeat with movement weights using [[Movement Challenge 2K7|MC2K7]], etc. | ||
Revision as of 18:38, 31 May 2012
DeBroglie Roadmap / Development notepad / Brainstorming Sandbox
- Precise Prediction + Wall Smoothing in order to calculate Precise MEAs and get ready for Wave Surfing.
- Dilemma - Roll my own or utilize someone else's?
- see User:Tkiesel/MovementPredictor
- Implement Wave Surfing
- Farewell Aristocles. You were a faithful friend, if a bit dodgy during round 1. ;)
- GoTo is what DeBroglie used to have, but TrueSurfing seems more philosophically satisfying at the moment...
- Danger function to include a term for field position? Corners are bad after all, and a slightly increased hit risk might be worth it to get out of a corner.
- Eventually, the pluggable EndPredictionCondition interface in MovementPredictor should make surfing multiple waves easier.. and allow me to handle cases like the following via a discrete Class that can handle the details:
- Wave A and Wave B are coming toward you. If you orbit clockwise or stop, Wave A will hit first. Remove Wave A and predict-surf remaining waves. If you orbit counter-clockwise, wave B will hit you first. Remove Wave B and predict-surf remaining waves
- Get a small Virtual Gun array going. Main GF gun, anti-adaptive GF gun, circular targeter, dead-stop targeter. For kicks. ;)
- Weight points in anti-adaptive gun via half-life based on round number.
- Pre-calculate decay exponentials and store in array. Just one extra array lookup and one extra multiplication per data point.. shouldn't be terribly slower than main gun.
- Test choosing gun via history of this shot (the k-nearest-neighbors can report which gun did best on them) vs. general history of the match.. Probably lots of trade-offs here.
- Weight points in anti-adaptive gun via half-life based on round number.
- Bullet Shadows (fairly easy with the Universe/Bot structure)
- Debug and Evaluate how the bot works in the Rumble without extensive tuning.
- Download and get RoboResearch working.
- Code a version of Debroglie to read/write dimension weights and real/virtual wave weighting from a .txt file. Let it chew on the Targeting Challenge RM bots for a week or two to explore the solution space.
- Pick the few best local maxima, do some runs that explore the space near them.
- Repeat all of this for the anti-adaptive gun with some relevant bots.
- Repeat with movement weights using MC2K7, etc.
