RougeDC/MovementLab - Robo Wiki -= Collecting Robocode Knowledge =-

Well, as a parallel to RougeDC/TargetingLab, here's the movement lab.

WaveSurfingChallenge2K6

RR Version MC Version Bot A Bot B Bot C Total Comment

Gamma4 MC01 96.22 98.18 97.53 97.31 1 season (500 Rounds)

MC03 99.94 98.33 95.98 98.08 1 season (500 Rounds)

MC04 100.00 98.72 96.58 98.43 1 season (500 Rounds)

MovementChallenge2K7/ResultsFastLearning

RR Version MC Version HOF SPL GRG Sub 1 WAY (Sub 2) GR3 RKM Sub 3 ASC CC CHK Sub 4 Total Comments

Alpha12 99.85 84.95 87.93 90.91 65.80 72.81 76.26 74.54 29.26 37.74 37.49 34.83 66.52 31.0 seasons

Alpha13 99.70 85.87 90.58 92.05 66.35 73.17 76.61 74.89 31.28 41.07 40.58 37.64 67.73 31.0 seasons

Alpha14 99.81 87.45 91.45 92.90 67.68 72.74 78.37 75.55 28.80 39.62 38.00 35.47 67.90 45.0 seasons

Alpha15 99.70 85.91 91.53 92.38 66.31 72.88 77.88 75.38 32.18 40.19 39.11 37.16 67.81 45.0 seasons

Gamma4 MC01 99.83 85.55 92.07 92.48 68.29 72.74 79.32 76.03 30.83 38.73 37.33 35.63 68.11 34.0 seasons

MC03 99.93 85.25 90.46 91.88 65.71 71.99 78.99 75.49 25.78 37.35 33.67 32.27 66.34 47.0 seasons

MC04 99.37 86.45 90.01 91.94 65.70 72.90 77.96 75.43 26.03 35.21 32.83 31.36 66.11 50.0 seasons

MC05 99.88 85.56 91.67 92.37 66.60 72.29 79.19 75.74 27.40 37.25 32.56 32.40 66.78 29.0 seasons

MC06 99.79 86.61 92.03 92.81 67.68 72.24 78.63 75.43 26.14 37.47 34.68 32.76 67.17 30.0 seasons

MC07 99.69 86.35 91.65 92.56 68.12 72.36 79.06 75.71 26.49 37.62 35.74 33.29 67.42 50.0 seasons

MC09 99.80 85.01 88.72 91.18 67.44 72.43 77.19 74.81 26.89 38.59 36.58 34.02 66.86 50.0 seasons

MC10 99.92 86.33 91.28 92.51 66.64 72.99 78.86 75.93 27.26 37.43 34.57 33.09 67.04 27.0 seasons

MC11 99.80 85.59 92.64 92.68 68.22 71.95 78.10 75.03 25.86 37.62 33.08 32.19 67.03 28.0 seasons

MC12 99.88 87.02 92.28 93.06 68.75 72.40 78.75 75.57 26.14 37.02 34.76 32.64 67.51 28.0 seasons

MC13 27.60 40.59 34.34 34.18 4.0 seasons

MC14 28.82 39.16 38.62 35.54 6.0 seasons

MC15 29.14 40.34 38.08 35.85 20.0 seasons

MC16 29.54 39.01 36.89 35.15 20.0 seasons

MC17 30.17 43.20 39.52 37.63 22.0 seasons

MC18 28.52 41.28 36.35 35.38 14.0 seasons

MC19 28.93 38.06 37.54 34.84 25.0 seasons

MC20 29.16 40.81 37.05 35.67 30.0 seasons

Version History:

MC01: The same as the movement in RougeDC Gamma4. While I didn't change the movement since Alpha15, there was a score increase, probably from a bugfix I made in my generic wave code somewhere along the way.
MC02: Trying an all new surfing algorithm that I think should handle all waves better. Still needs work, the results were not worth recording even.
MC03: The same all new surfing algorithm as in MC02, however using the old danger formula from MC01, and works far better than MC02. It still performs worse than MC01 for the most part though, interestingly though, it gets a HOF score among the very highest there is. To me this indicates that it's better quality surfing but that the danger formula needs work to tune it to it probably...
MC04: Some tweaks to the danger formula. Seems to help some though the Bot C performance still isn't great.
MC05: Remove all but one tweak to the danger formula (making it pickier about how far away the DC match is). Bah... still a lot of work needed...
MC06: Change cluster size to 10 (from 20). Seems to have a nice effect overall.
MC07: First try with adding a neural net to the mix. I'm now suspecting that the improvements were mostly from just making it trickier for adaptive guns to understand my movement.
MC08: Attempts to make the neural net work better. Failed attempts not worth recording...
MC09: Replace the neural net with linear regression... doesn't seem to do much good...
MC10: Surf both adjusted and non-adjusted values.
MC11: MC06 plus one interpolated value.
MC12: MC06 plus a distance segment.
MC13: First attempt at building a flattener. Disable all stats except the flattener.
MC14: 50/50 balance of flattener and normal stats. Whoops... that was still pure flattener I think...
MC15: Fixed the 50/50 balance to work right, and increase cluster size to 20 for the flattener...
MC16: Switch the flattener to a movement profile system matching my gun.
MC17: Based on MC15. Add a "prefer newer data segment".
MC18: Cut advancing velocity segment in half and add an acceleration segment.
MC19: Remove the acceleration segment, but keep the advancing velocity cut to MC18 levels.
MC20: Revert advancing velocity level, but re-add the acceleration segment.

Discussion

Gahhh.... even though MC04 didn't hurt head-on performance according to WSC2K6, it's HOF performance took a major nosedive in MC2K7. The changes there were helpful to the Splinter and GrubbmThree performance but not much else. The surfer performance could surely be helped a great deal by a flattener, but I should first get my scores in "Sub 1" and "Sub3" up to decent levels I think... -- Rednaxela

Haha! The upcoming MC07 adds a NeuralNetwork to the mix, and results so far seem to show it as an improvement. What could it possibly offer a DC surfing? Well, The way I see it, normal DynamicClustering, is far from optimal against simple linear-targeting. The problem, is that for it to be accurate, it needs an awful lot of data samples (at least one at just about any velocity you may expect to be moving at) to produce good results, and it's inherently incapable of making guesses at gf values it has not seen before. Well, to solve that I added a simple back-propagation net. It's designed to find general trends in how the segment data tends to affect the guessfactor. Instead of just weighting results from DC lower when the situation is further from the current situation, I also use the neural net to reposition the guessfactors that the DC spits out, to be more relevant to the current situation. Wow... my bot is really tending to hybridize things all over the place. Actually, I find hybridizing far more pleasant than tuning, it's both more interesting and seems to get me results quicker. My targeting is DC/PM and my surfing is now DC/NN. I think this could likely be the first high ranking bot that uses both DC, PM, and NN learning/prediction techniques. Anyways, I'll post the MC07 results when I have 30 seasons I think. I think there's certainly room for improvement in the neural net though, such as trying out my "multiple plane regression clustering" idea to cluster multiple neural nets in order to more accurately model multi-mode targeters. -- Rednaxela

Well, it seems like my ideas to "focus" the data with a neural net or linear regression have kind of failed. They don't seem to actually do much except confuse adaptive guns somewhat. I'm thinking now that I might attempt to overlay a couple DC-trees with different segmentations. Well... or just before I let the focusing idea die, I might try overlaying it with the non-focused data at the same time and see how that does... -- Rednaxela

Apparently, my flattener really sucks! Hooray! Time to figure out what sucks so much about it... -- Rednaxela

Try weighting your flattener 50/50 with your main stats - that's what worked best for me. -- Skilgannon

Just tried it now. That seems to improve results a bit, however I think I can still safely conclude that my flattener really sucks. I do have a few ideas to test for improving it though... -- Rednaxela
Update: Whoops, that was pure flattener again still I think. Running a new test now, with 50/50 weighting, and the cluster size for the flattener increased to 20... -- Rednaxela
Update: Okay! It appears my flattener does indeed still suck just like I thought. To fix it, I'm thinking of making it so, instead of dodging specific points the DC returns, it will dodge a "hit range profile", basically what my gun uses. In other words, I'll make my flattener into something that's more of a model of my own DC gun. At very least, It'll be better at dodging myself, and I also suspect that processing DC stats this way will give results closer to VCS too. -- Rednaxela
Update: And... that doesn't seem to help... -- Rednaxela

What attributes are you clustering your flattener on? The important ones are distance (because their guns use it), acceleration, and lateral velocity. Throwing in a time-based attribute also helps. What you're trying to do is create a copy of their gun. -- Skilgannon

Currently I use distance, lateral velocity, and advancing velocity, and a very very light segment on how many waves have been fired before this one (just strong enough to prefer new data over old). I guess I might see if acceleration helps, but I'm not sure it will because FloodGrapher appears to show me as reasonably flat in that segment too I think. -- Rednaxela

I see you've increased the number of points surfed - are you weighting them by the inverse euclidean distance squared? Have you tried other methods, like inverse 'absolute value' distance, etc? Be careful of trusting FloodGrapher on surfing matters - it takes every single wave, and not just the waves with bullets, as a strong anti-surfer gun would (Ascendant, Dookious, Phoenix, etc). Try weighting advancing velocity lower, I don't think many anti-surfer guns use that one. Time-based attributes (also weighted low) prevent pattern matchers from picking up on your movement, as well as confusing the higher-legion "every single tick" guns like Shadow and Dookious's main gun. I found that multiplying the distance by how many hits ago the data was recorded was an effective way of preferring new data over old. DrussGT/ChallengeResults shows some interesting info - take a look at the lower MC2K7 section, testing out DC movement. -- Skilgannon

Well, I actually didn't have my "prefer new data" segment in MC15/16, and adding that seems to have helped significantly. I didn't need such a segment in my normal surfing because there isn't enough data for old data to flood the nearest-neighbors, but there are far more data points for a flattener of course. So still not quite there yet, but getting closer. Multiplying the distance by how many hits ago the data was recorded sounds interesting however I prefer my approach of making it a very weakly weighted segment, because when doing DC it's possible that all of the selected data points might be very old without that preference. As far as the weighting of points, I'm currently sticking with the same thing that I tuned for my normal surfing. It's a bit overcomplicated and messy my danger formula, but I'd rather change it for both the surfing and flattening at once some other time to keep it in sync and avoid code duplication. I think that next, I'll try acceleration, wall, and time-based segments. Also, I might be wrong, but I'm pretty sure FloodGrapher only uses real bullet waves, not tick waves, because Kawigi said "FloodMini 1.4 is a fine test bot with a FloodGrapher plugin (but it's not necessarily accurate, since it fires waves every scan). The preferred way it to use kawigi.tools.FloodGrapher" on the FloodGrapher page. -- Rednaxela

Would you believe I've almost never used MovementProfile graphing? I tried it briefly waaay back, but not since having any decent WaveSurfing movement. I dunno, it definitely seems super useful for tuning a RandomMovement, but I just am not sure it tells you much useful info about a surfer. A WaveSurfer can control its movement profile at will, so the profile is almost 100% dictated by the gun you're facing, right? Or am I missing something? -- Voidious

The only trouble is that this assumes that the gun you are surfing is the same as the gun that is shooting at you =) So I think, once you get your precise prediction up to scratch, the next part of the challenge is making a 'gun' that can simulate *any* other gun as accurately as possible. This of course requires tweaking weights, messing with different attributes, and adding a flattener to simulate a gun with rolling averages. But yeah, I think I've graphed DrussGT once, around 0.3.10, and that was just for laughs =) -- Skilgannon

Well, I would say graphing is pointless against normal WaveSurfing, however I don't think that's the case if it's put in "pure" flattener mode. If I disable all non-flattener stats like I did at once point, I believe MovementProfile graphing should roughly give an idea of how good the surfing movement actually is at controlling it's profile. -- Rednaxela

Ah, yeah, you both make good points. Thanks for humoring a senile old Robocoder. =) -- Voidious

I wonder if it's your old age that makes you keep forgetting to re-release Dookious? ;-) And I gotta ask, Rednaxela, how many hours a day are you spending on Robocode?!? The pace you're going at makes me believe that you're coding full time! I can only take so many hours a day... -- Skilgannon

Haha, well lately my laptop is running RoboResearch nearly 24/7 but my body isn't quite spending as much time. At least 90% of the time I'm fighting off the temptation to core more ideas to improve it and be patient for running a RoboResearch test to finish. I suppose it's a good thing it takes so long to run a research test, because it forces me to pace myself so I don't get burnt out so much. Also, it is summer break, I haven't found a summer job thus far, and I lack a social life... so... well... yeah... =) -- Rednaxela

Let me guess, MC20 will have the acceleration attribute, but will return the advancing velocity to MC17 levels? =) -- Skilgannon

Yep! 8 seasons have run so far though and the score is only 35.8, so it's not looking like acceleration is very helpful, but I'll wait till I have at least 20 seasons before dismissing it. -- Rednaxela

RR Version	MC Version	Bot A	Bot B	Bot C	Total	Comment
Gamma4	MC01	96.22	98.18	97.53	97.31	1 season (500 Rounds)
	MC03	99.94	98.33	95.98	98.08	1 season (500 Rounds)
	MC04	100.00	98.72	96.58	98.43	1 season (500 Rounds)

RR Version	MC Version	HOF	SPL	GRG	Sub 1	WAY (Sub 2)	GR3	RKM	Sub 3	ASC	CC	CHK	Sub 4	Total	Comments
Alpha12		99.85	84.95	87.93	90.91	65.80	72.81	76.26	74.54	29.26	37.74	37.49	34.83	66.52	31.0 seasons
Alpha13		99.70	85.87	90.58	92.05	66.35	73.17	76.61	74.89	31.28	41.07	40.58	37.64	67.73	31.0 seasons
Alpha14		99.81	87.45	91.45	92.90	67.68	72.74	78.37	75.55	28.80	39.62	38.00	35.47	67.90	45.0 seasons
Alpha15		99.70	85.91	91.53	92.38	66.31	72.88	77.88	75.38	32.18	40.19	39.11	37.16	67.81	45.0 seasons
Gamma4	MC01	99.83	85.55	92.07	92.48	68.29	72.74	79.32	76.03	30.83	38.73	37.33	35.63	68.11	34.0 seasons
	MC03	99.93	85.25	90.46	91.88	65.71	71.99	78.99	75.49	25.78	37.35	33.67	32.27	66.34	47.0 seasons
	MC04	99.37	86.45	90.01	91.94	65.70	72.90	77.96	75.43	26.03	35.21	32.83	31.36	66.11	50.0 seasons
	MC05	99.88	85.56	91.67	92.37	66.60	72.29	79.19	75.74	27.40	37.25	32.56	32.40	66.78	29.0 seasons
	MC06	99.79	86.61	92.03	92.81	67.68	72.24	78.63	75.43	26.14	37.47	34.68	32.76	67.17	30.0 seasons
	MC07	99.69	86.35	91.65	92.56	68.12	72.36	79.06	75.71	26.49	37.62	35.74	33.29	67.42	50.0 seasons
	MC09	99.80	85.01	88.72	91.18	67.44	72.43	77.19	74.81	26.89	38.59	36.58	34.02	66.86	50.0 seasons
	MC10	99.92	86.33	91.28	92.51	66.64	72.99	78.86	75.93	27.26	37.43	34.57	33.09	67.04	27.0 seasons
	MC11	99.80	85.59	92.64	92.68	68.22	71.95	78.10	75.03	25.86	37.62	33.08	32.19	67.03	28.0 seasons
	MC12	99.88	87.02	92.28	93.06	68.75	72.40	78.75	75.57	26.14	37.02	34.76	32.64	67.51	28.0 seasons
	MC13									27.60	40.59	34.34	34.18		4.0 seasons
	MC14									28.82	39.16	38.62	35.54		6.0 seasons
	MC15									29.14	40.34	38.08	35.85		20.0 seasons
	MC16									29.54	39.01	36.89	35.15		20.0 seasons
	MC17									30.17	43.20	39.52	37.63		22.0 seasons
	MC18									28.52	41.28	36.35	35.38		14.0 seasons
	MC19									28.93	38.06	37.54	34.84		25.0 seasons
	MC20									29.16	40.81	37.05	35.67	30.0 seasons