Author |
Topic: DAPE - Depreciated Arimaa Piece Evaluator (Read 6306 times) |
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
DAPE - Depreciated Arimaa Piece Evaluator
« on: Nov 9th, 2006, 9:24pm » |
Quote Modify
|
Announcing the latest material evaluation function. Basically each piece is valued according to: * how many enemy pieces are stronger than it ("above"), and * how many enemy pieces are equal in strength ("equal"). The score for each piece is simply: score = A/(S+E*equal+above); Where A, S, and E are all constants. E must be in the interval (0,1), A and S should both be positive. Suggested starting values are given below. A fairly ad-hoc correction for what happens when you run short of rabbits is then added, but this could be further refined. Toby Code: double DAPE(position *p) { int typ, c, e; double Amplitude = 18.0; double Shift = 0.25; double Equal_mult = 0.3; /* count the number of colour c pieces that are above or equal this value */ int above[2]; int equal[2]; double score[2]; above[0] = 0; above[1] = 0; equal[0] = 0; equal[1] = 0; score[0] = 0.0; score[1] = 0.0; for (typ=6; typ>=1; typ--) { for (c=0; c<2; c++) { above[c] += equal[c]; equal[c] = bc2(p->bd[c][typ]); } for (c=0; c<2; c++) { e = c ^ 1; score[c] += equal[c]*Amplitude/(Shift+Equal_mult*equal[e]+above[e]); } } /* now special penalties if the number of rabbits gets too low */ score[0] -= 40.0*pow(0.6,equal[0]); score[1] -= 40.0*pow(0.6,equal[1]); /* DRAW ANALYSIS SHOULD BE INCLUDED IN FINAL PROGRAM */ return (score[1]-score[0]); } |
|
|
« Last Edit: Nov 9th, 2006, 9:26pm by 99of9 » |
IP Logged |
|
|
|
Fritzlein
Forum Guru
Arimaa player #706
Gender:
Posts: 5928
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #1 on: Nov 9th, 2006, 10:35pm » |
Quote Modify
|
So what are some consequences? Does DAPE like M or HD? D or RR? Where does it work better than FAME? (Not that FAME is hard to beat, but I'm curious about the specifics...)
|
|
IP Logged |
|
|
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #2 on: Nov 9th, 2006, 11:03pm » |
Quote Modify
|
Here's one of Janzert's funky calculators for it: http://members.westnet.com.au/doctorhudson/arimaa/dape.html (I hope there's no bugs, I wrote it quickly, and I don't actually know javascript) I can't remember why I thought it was better! I invented it a couple of months ago, and tried some specific predictions, but you'll have to make that judgement for yourself.
|
|
IP Logged |
|
|
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #3 on: Nov 9th, 2006, 11:28pm » |
Quote Modify
|
Well, I've already found one bug. If you've already killed an M and given away your HD (which the current constants of DAPE thinks is favourable), DAPE then recommends: 1) Trade elephants (correct) 2) Trade horses (??) 3) Do not trade dogs (??) 4) Trade rabbits (wrong) The problem is, I can't easily fix #4 just by changing constants...
|
« Last Edit: Nov 9th, 2006, 11:29pm by 99of9 » |
IP Logged |
|
|
|
Fritzlein
Forum Guru
Arimaa player #706
Gender:
Posts: 5928
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #4 on: Nov 10th, 2006, 8:40am » |
Quote Modify
|
on Nov 9th, 2006, 11:28pm, 99of9 wrote:If you've already killed an M and given away your HD (which the current constants of DAPE thinks is favourable), DAPE then recommends: 1) Trade elephants (correct) 2) Trade horses (??) 3) Do not trade dogs (??) 4) Trade rabbits (wrong) |
| I haven't played a unbalanced M for HD (or HC) game in a while. Perhaps shifting strategies have made them less common. But even so I'm quite confident that when you have M for HD, you do not want to trade horses. I just checked out the cool DAPE calculator, and DAPE agrees with me. In fact, it thinks trading horses there is even more catastrophic for the side with camel than I think it is. I think you must have made a mistake in reporting that one. I agree with you that the camel side doesn't want to trade rabbits (and thus disagree with DAPE), but I don't feel strongly about that. Rabbit trades are still pretty much equal in that situation. FAME has a teeny tiny bias against trading rabbits, and I think that's both the right direction and the right magnitude. It's interesting that DAPE clearly prefers a dog to two initial rabbits and a horse to three initial rabbits. Thus it values pieces more relative to rabbits than FAME, at least in the early going.
|
|
IP Logged |
|
|
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #5 on: Nov 10th, 2006, 4:28pm » |
Quote Modify
|
on Nov 10th, 2006, 8:40am, Fritzlein wrote: I just checked out the cool DAPE calculator, and DAPE agrees with me. In fact, it thinks trading horses there is even more catastrophic for the side with camel than I think it is. I think you must have made a mistake in reporting that one. |
| Oh, good, you're right. Sorry about that. Quote:It's interesting that DAPE clearly prefers a dog to two initial rabbits and a horse to three initial rabbits. Thus it values pieces more relative to rabbits than FAME, at least in the early going. |
| In my judgement DAPE is correct on both of these, but I don't feel so strongly to call that an error by FAME. DAPE knows that these trades get less valuable when material goes off the board, and soon discourages them.
|
« Last Edit: Nov 10th, 2006, 4:29pm by 99of9 » |
IP Logged |
|
|
|
Janzert
Forum Guru
Arimaa player #247
Gender:
Posts: 1016
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #6 on: Nov 13th, 2006, 3:08pm » |
Quote Modify
|
The FAME calculator now does both FAME and DAPE and needs a name change, probably AMES calculator. Hopefully it will grow IdahoEV's naive evaluator soon as well. The one discrepancy that stood out to me while working on it was H for CC, FAME slightly prefers losing the horse while DAPE would rather lose the cats. Janzert
|
|
IP Logged |
|
|
|
Fritzlein
Forum Guru
Arimaa player #706
Gender:
Posts: 5928
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #7 on: Nov 13th, 2006, 8:40pm » |
Quote Modify
|
Thanks, Janzet. I'm going to have fun with that. Since everyone found a bunch of flaws in FAME after it came out, I especially want to give DAPE a rude reception. Let me point out that in ERR vs dccrr, Gold is clearly losing, but DAPE says Gold is clearly winning. It's funny that FAME thinks a free cat is worth 1.49 and a free horse is worth 3.12 (more than 2 * 1.49) but nevertheless slightly prefers two free cats to a horse. I might slightly prefer the horse myself, but IdahoEv's research currently seems to be favoring small pieces, so I may be further wrong than FAME.
|
|
IP Logged |
|
|
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #8 on: Nov 13th, 2006, 11:00pm » |
Quote Modify
|
Nice job janzert. In response to Fritz's position, and the general trading down failures, I've updated the formula on my version of the calculator: http://members.westnet.com.au/doctorhudson/arimaa/dape.html It now includes a term similar to the low-rabbit penalty, which is basically a low-piece penalty. I've also adjusted the coefficients a bit to accommodate the change. Would you mind including this alteration for me Janzert? Sorry, it's a bit of an iterative process.
|
|
IP Logged |
|
|
|
Janzert
Forum Guru
Arimaa player #247
Gender:
Posts: 1016
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #9 on: Nov 14th, 2006, 2:59am » |
Quote Modify
|
No problem, I rather expect it to change for a bit yet. Now updated. Also updated the constant to normalize the initial rabbit capture. Also when I added DAPE in I got rid of the raw score display altogether since comparing them directly doesn't really make any sense. Janzert
|
|
IP Logged |
|
|
|
99of9
Forum Guru
Gnobby's creator (player #314)
Gender:
Posts: 1413
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #10 on: Nov 14th, 2006, 4:07am » |
Quote Modify
|
Thanks Janzert. The biggest disagreements I've found so far are: dape | fame | correct | ERR | EMR | ? | EMHDDCC8R | EMHHDDC6R | ? | EHDDCC8R | EMHHDDCC | dape | EMHHC8R | EHHDDCC8R | fame? | EMHHCC7R | EHHDDCC8R | ? | EHHDDCxR | EMDDCCxR | ? | EHC4R | EMD3R | ? | | | | | | | I'll add more to the list when people mention them.
|
« Last Edit: Nov 14th, 2006, 4:41am by 99of9 » |
IP Logged |
|
|
|
mattj256
Forum Guru
Arimaa player #8519
Gender:
Posts: 138
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #11 on: May 3rd, 2013, 3:41am » |
Quote Modify
|
I was looking online at the piece evaluator. Did you know that for R vs EMHHDDCC most of the material evaluators say that Silver is winning even though Silver has no rabbits left? Is there a deeper issue here or is it strictly a theoretical concern? It's not like the situation I described is going to happen in a real game...
|
|
IP Logged |
|
|
|
supersamu
Forum Moderator Forum Guru
Arimaa player #7523
Gender:
Posts: 140
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #12 on: May 4th, 2013, 3:38am » |
Quote Modify
|
You can´t trust material evaluators when 8 rabbits are of the board. There is no "deeper issue" there. What also is weird is this: - when gold has a handicap of 8 rabbits, and silver has only one piece left, a rabbit, FAME thinks gold is ahead by 22.51. - when gold has a handicap of 8 rabbits, and silver has no pieces left, FAME thinks the teams are even. So FAME would recommend for silver to sacrifice his last piece in the situation descibed above. But as I said, these are issues that only come up when one team has no rabbits on the board. There was a rulechange that made the player with no rabbits left immediately lose the game. But this rulechange happened after FAME and DAPE were developed. Conclusion: Material Evaluators use a formula to evaluate the position and when there are 0 rabbits left, the formula doesn´t work in the intended way.
|
|
IP Logged |
|
|
|
mattj256
Forum Guru
Arimaa player #8519
Gender:
Posts: 138
|
|
Re: DAPE - Depreciated Arimaa Piece Evaluator
« Reply #13 on: May 4th, 2013, 4:04am » |
Quote Modify
|
Cool thanks.
|
|
IP Logged |
|
|
|
|