Difference between revisions of "User:Simonton/PFResearch"

From Robowiki
Jump to navigation Jump to search
m (More results)
(0069 & 0070)
Line 159: Line 159:
 
* '''0068:''' Same dimensions as 67, but pieces the cluster together from smaller clusters using every combination of segments that include lateral velocity.
 
* '''0068:''' Same dimensions as 67, but pieces the cluster together from smaller clusters using every combination of segments that include lateral velocity.
 
* '''0069:''' Slightly different travel angle calculation, to (hopefully) smooth out the wall approach slightly.  As a side effect, lessens the retreat angle when too close to the enemy (and increases attack angle when too far away).
 
* '''0069:''' Slightly different travel angle calculation, to (hopefully) smooth out the wall approach slightly.  As a side effect, lessens the retreat angle when too close to the enemy (and increases attack angle when too far away).
 +
* '''0070:''' Bugfix to time-since-orientation change dimension (it was only working clockwise).  0067 + smoother angles of 0069.
 +
* '''0071:''' Add back splicing of smaller clusters from 0069.
 +
* '''0072:''' Using combinations of dimensions for weighting, instead of making separate clusters for each.

Revision as of 15:13, 15 September 2008

My next experiment: goto path surfing. It works by choosing (currently) 31 impact points on each wave, spread out across GF -1 to 1, then plotting the path through them with the least sum of the dangers. It currently works like this, which will become more sophisticated with time:

  • For each Wave choose 31 GuessFactors, spread out across GFs -1 to 1, being sure to include local minimum danger points.
  • To find the best path from a given point:
    • Find the next wave to strike that point.
    • Find the points on that wave that meet the 31 chosen GFs AND could be reached from this point along the path of maximum escape.
    • Recurse to find the danger of each of those points.
    • Choose the point with the least danger.
    • Add in the danger of this point, add this point to the best path so far, and return.

So far there's very humble beginnings:

See old results at /DCGTResearchArchive

MC2K7 Fast Learning Results

Bot Name Author Type HOF SPL GRG Sub 1 WAY (Sub 2) GR3 RKM Sub 3 ASC CC CHK Sub 4 Total Comments
0038 Simonton PF/DC 99.23 85.89 86.57 90.56 62.90 53.18 68.64 60.91 34.39 42.98 40.12 39.16 63.38 90.0 seasons
0039 Simonton PF/DC 99.75 85.78 87.29 90.94 64.62 53.05 69.49 61.27 34.71 40.46 39.79 38.32 63.79 90.0 seasons
0040 Simonton PF/DC 99.75 85.90 86.73 90.79 65.18 52.27 70.25 61.26 34.24 41.26 39.97 38.49 63.93 78.8 seasons
0043 Simonton PF/DC 99.79 86.22 86.52 90.84 64.50 58.29 69.33 63.81 35.01 42.12 38.60 38.58 64.43 90.0 seasons
0044 Simonton PF/DC 99.73 85.94 87.65 91.11 62.40 51.78 68.58 60.18 34.67 41.63 41.56 39.29 63.24 83.9 seasons
0045 Simonton PF/DC 99.81 85.86 86.95 90.87 64.27 54.76 67.83 61.30 35.02 42.20 38.85 38.69 63.78 75.0 seasons
0046 Simonton PF/DC 99.54 87.36 89.06 91.99 63.60 55.20 70.14 62.67 33.75 41.25 39.07 38.02 64.07 75.0 seasons
0047 Simonton PF/DC 99.69 87.79 88.84 92.11 65.00 55.51 71.39 63.45 33.42 41.14 39.05 37.87 64.61 75.0 seasons
0048 Simonton PF/DC 99.65 86.84 87.68 91.39 63.82 58.86 68.81 63.83 34.65 41.52 38.23 38.13 64.29 75.0 seasons
0050 Simonton PF/DC 99.67 87.82 89.03 92.17 63.19 57.96 72.58 65.27 33.19 40.94 39.39 37.84 64.62 75.0 seasons
0051 Simonton PF/DC 99.73 86.94 88.40 91.69 62.81 60.33 70.47 65.40 34.12 41.34 38.56 38.01 64.48 75.0 seasons
0052 Simonton PF/DC 99.70 87.79 89.77 92.42 61.73 57.98 72.82 65.40 30.41 41.93 39.99 37.44 64.25 75.0 seasons
0053 Simonton PF/DC 99.71 87.95 88.69 92.12 62.85 58.24 72.11 65.18 33.68 41.07 40.03 38.26 64.60 75.0 seasons
0054 Simonton PF/DC 99.64 87.66 89.17 92.15 63.04 60.42 72.20 66.31 33.01 41.69 39.29 38.00 64.88 75.0 seasons
0056 Simonton PF/DC 99.72 86.65 87.72 91.37 61.41 60.22 71.07 65.64 31.93 38.37 37.65 35.98 63.60 75.0 seasons
0057 Simonton PF/DC 99.56 88.14 86.88 91.53 65.95 62.77 75.40 69.08 34.95 42.30 40.09 39.11 66.42 75.0 seasons
0058 Simonton PF/DC 99.51 87.62 87.97 91.70 64.39 61.66 75.21 68.44 34.93 43.53 39.35 39.27 65.95 75.0 seasons
0059 Simonton PF/DC 99.53 88.25 87.34 91.71 67.40 63.42 76.11 69.76 35.03 42.28 40.35 39.22 67.02 75.0 seasons
0060 Simonton PF/DC 99.47 88.79 88.33 92.20 67.67 63.39 76.99 70.19 35.82 41.39 40.17 39.13 67.30 75.0 seasons
0061 Simonton PF/DC 99.80 88.45 89.72 92.66 69.63 63.29 76.61 69.95 34.52 41.29 41.34 39.05 67.82 75.0 seasons
0062 Simonton PF/DC 99.98 88.02 89.75 92.59 68.40 63.20 76.18 69.69 33.00 40.64 39.98 37.88 67.14 75.0 seasons
0063 Simonton PF/DC 99.97 88.59 89.93 92.83 67.91 63.30 77.67 70.48 33.43 40.42 40.10 37.98 67.30 75.0 seasons
0064 Simonton PF/DC 99.99 88.10 88.74 92.28 68.93 62.83 77.27 70.05 34.86 41.15 40.69 38.90 67.54 75.0 seasons
0065 Simonton PF/DC 99.96 87.89 88.98 92.28 69.17 62.83 77.79 70.31 34.00 42.49 41.87 39.45 67.80 75.0 seasons
0066 Simonton PF/DC 99.99 88.27 88.78 92.34 69.28 63.16 76.50 69.83 34.36 40.22 40.27 38.28 67.43 75.0 seasons
0067 Simonton PF/DC 99.98 88.00 89.35 92.44 69.28 63.19 78.40 70.80 34.96 41.76 42.00 39.57 68.02 75.0 seasons
0068 Simonton PF/DC 99.97 87.64 90.31 92.64 68.70 63.82 78.27 71.04 36.20 42.71 42.85 40.59 68.24 75.0 seasons
0069 Simonton PF/DC 99.96 87.72 91.49 93.06 68.61 63.41 79.12 71.27 33.84 41.48 43.23 39.52 68.11 75.0 seasons
0070 Simonton PF/DC 99.95 87.65 91.89 93.17 70.09 63.20 80.43 71.82 34.34 41.19 41.68 39.07 68.53 75.0 seasons
Bot Name Author Type HOF SPL GRG Sub 1 WAY (Sub 2) GR3 RKM Sub 3 ASC CC CHK Sub 4 Total Comments
DrussGT 1.1.4 Skilgannon WS-GT VCS 99.70 87.77 92.74 93.41 71.54 71.51 81.64 76.57 43.10 49.21 47.69 46.67 72.05 100.0 seasons
Dookious 1.554 Voidious WS 99,94 86,30 94,31 93,52 69,07 69,41 84,12 76,76 40,73 52,86 52,06 48,55 71,97 31 seasons
DrussGT w/ my "segments" Skilgannon WS-GT 99.42 87.56 90.58 92.52 65.73 73.56 78.44 76.00 33.28 41.70 41.90 38.96 68.30 41.0 seasons
Firebird 0.1 David Alves DC WS 99.88 87.01 86.72 91.21 67.16 64.53 77.10 70.82 30.02 42.54 42.16 38.24 66.85 100.0 seasons

MC2K7 Results

Bot Name Author Type HOF SPL GRG Sub 1 WAY (Sub 2) GR3 RKM Sub 3 ASC CC CHK Sub 4 Total Comments
0038 Simonton PF/DC 99.36 88.34 89.60 92.43 69.57 54.90 67.37 61.14 28.22 42.45 31.23 33.96 64.28 5.0 seasons
0039 Simonton PF/DC 99.84 88.24 90.17 92.75 72.19 55.53 70.44 62.99 29.23 43.84 30.75 34.61 65.63 5.0 seasons
0040 Simonton PF/DC 99.84 87.94 90.16 92.65 71.52 53.87 71.52 62.69 27.79 40.68 28.40 32.29 64.79 5.0 seasons
0050 Simonton PF/DC 99.71 89.18 91.72 93.54 70.25 58.55 71.27 64.91 27.11 43.43 30.33 33.62 65.58 5.0 seasons
0051 Simonton PF/DC 99.77 89.50 91.57 93.61 70.41 60.91 70.33 65.62 27.05 43.33 29.22 33.20 65.71 5.0 seasons
0052 Simonton PF/DC 99.82 89.96 91.83 93.87 69.06 59.18 72.36 65.77 22.82 43.24 29.21 31.76 65.12 2.8 seasons
0053 Simonton PF/DC 99.75 89.19 91.61 93.52 70.40 58.72 73.40 66.06 28.44 41.78 29.35 33.19 65.79 5.0 seasons
0056 Simonton PF/DC 99.68 88.24 90.99 92.97 68.65 60.69 70.21 65.45 26.58 42.10 29.40 32.69 64.94 5.0 seasons
0057 Simonton PF/DC 99.58 90.04 91.69 93.77 72.55 63.46 75.32 69.39 28.14 43.87 30.54 34.18 67.47 5.0 seasons
0058 Simonton PF/DC 99.67 89.60 91.63 93.63 73.33 62.53 75.72 69.13 29.83 42.90 29.69 34.14 67.56 5.0 seasons
0059 Simonton PF/DC 99.56 90.46 92.30 94.11 73.40 64.25 77.79 71.02 29.97 44.41 30.94 35.11 68.41 5.0 seasons
0061 Simonton PF/DC 99.86 90.98 93.01 94.61 75.32 64.53 77.14 70.84 29.88 42.86 30.56 34.43 68.80 5.0 seasons
0062 Simonton PF/DC 99.99 90.45 92.12 94.19 74.25 64.31 78.52 71.41 25.95 40.19 28.72 31.62 67.87 5.0 seasons
0063 Simonton PF/DC 99.99 90.56 93.85 94.80 75.04 64.55 79.79 72.17 27.31 41.64 29.03 32.66 68.67 5.0 seasons
0064 Simonton PF/DC 100.00 89.76 93.54 94.43 74.98 63.54 80.64 72.09 27.27 42.39 29.66 33.11 68.65 1.9 seasons
0068 Simonton PF/DC 99.98 89.41 94.20 94.53 74.90 64.79 82.13 73.46 29.51 45.83 33.12 36.16 69.76 5.0 seasons
0069 Simonton PF/DC 100.00 90.17 96.00 95.39 73.86 64.04 82.50 73.27 27.86 42.64 31.41 33.97 69.12 1.0 seasons
Bot Name Author Type HOF SPL GRG Sub 1 WAY (Sub 2) GR3 RKM Sub 3 ASC CC CHK Sub 4 Total Comments
DrussGT 0.3.1 Skilgannon WS-GT 99.87 89.16 96.42 95.15 69.93 66.81 86.20 76.50 24.34 52.48 37.66 38.16 69.94 1 season
Dookious 1.554 Voidious WS/GF 99.92 89.18 98.03 95.71 72.86 70.23 87.95 79.09 30.78 54.23 40.02 41.67 72.33 6 seasons

Versions

  • 0038: Considers points on a wave that it must drive through to reach (without coming to a stop).
  • 0039: Add back DiveProtection again.
  • 0040: 0038 with added danger for taking up more GFs (i.e. being closer), instead of explicit DiveProtection.
  • 0043: 0041, fixed back to the danger calculation I've been using.
  • 0044: 0042, fixed back to the danger calculation I've been using.
  • 0045: Putting together features of 0039 (DiveProtection), 0043 (distancing) & 0044 (harmless EnergyDrop wave)
  • 0046: Finally found a couple of those off-by-one errors Skilgannon has been figuring I have! 0038 with those (hopefull?) fixed. Thanks to Rednaxela for the conversation that prompted me to look for these.
  • 0047: 0046 with DiveProtection (0039 w/out the off-by-one bugs)
  • 0048: 0046 with angle-based distancing (0043 w/out the off-by-one bugs)
  • 0050: 0046 w/ speed optimization/bugfix: only recaclulate the path when something changes. Recalculating every tick threw off predictions for any destination generation that depended on distance.
  • 0051: angle-based distancing
  • 0052: 0050 but travels perpendicular to the line (wave origin, point on last wave), rather than the line for GF0.
  • 0053: 0050 but don't turn toward the next destination when there will be enough time to do so later.
  • 0054: 1) Don't fire an enemy wave the same tick as a collision (it's complicated to figure out if you should, and you can't surf a wave that close anyway). 2) Don't turn toward the "retreat point" when sitting still waiting for the energy drop wave (since no real waves are in the air), to avoid having to turn right back to perpendicular once he fires.
  • 0055: Linearly normalize wave dangers to 0-1. This will give much higher danger to "clumped" waves than those spread out. on second thought, it will be no different.
  • 0056: Normalize dangers to 0-1 by taking danger from nearest logged gf. This will give no higher to "clumped" waves.
  • 0057: 0054 + Accellerates before pointing straight at its destination.
  • 0058: Add 1% noise to wave dangers. I don't have high hopes for this, but am still very interested to see the results.
  • 0059: 0057 + add back gunheat surfing when there are 0 or 1 other in-flight waves, except this time doing it correctly! (hopefully) Thanks for the tips, Rednaxela!
  • 0060: Surf the gunheat wave no matter how many other waves are in-flight.
  • 0061: Angle-based distancing (preferred 500), based off perpendicular from the line of the last destination to center of the next wave.
  • 0062: Different danger calculation that accounts for closeness taking up more "bins".
  • 0063: Add distance dimension.
  • 0064: Add time-since-direction-change dimension.
  • 0065: Switch the time-since to the almost-equivalent (but maybe importantly different) time-since-orientation-change.
  • 0066: Use only lateral velocity dimension.
  • 0067: Dimensions: Lateral velocity, forward wall distance, distance, time since orientation change
  • 0068: Same dimensions as 67, but pieces the cluster together from smaller clusters using every combination of segments that include lateral velocity.
  • 0069: Slightly different travel angle calculation, to (hopefully) smooth out the wall approach slightly. As a side effect, lessens the retreat angle when too close to the enemy (and increases attack angle when too far away).
  • 0070: Bugfix to time-since-orientation change dimension (it was only working clockwise). 0067 + smoother angles of 0069.
  • 0071: Add back splicing of smaller clusters from 0069.
  • 0072: Using combinations of dimensions for weighting, instead of making separate clusters for each.