17:
132:
Researchers decided to make an AI model that played a "simplified", single-player variant of mahjong; this model was intended to provide a framework for other models to use. They considered their model "greedy" because it only focused on winning itself. The researchers later added a second player,
118:
Researchers took note of the complexity involved in mahjong's scoring system and attempted to make an AI that could recognize the components of a winning hand and calculate the score with the goal of helping people restrained by their old age. Because this AI model attempted to recognize tiles in
31:(AI), there are several factors researchers must consider; an AI must take into account its own hand as well as what it infers about the other players' hands utilizing the information available. Researchers have developed several mahjong-related AI models with various applications.
330:
Junjie Li; Sotetsu
Koyamada; Qiwei Ye; Guoqing Liu; Chao Wang; Ruihan Yang; Li Zhao; Tao Qin; Tie-Yan Liu; Hsiao-Wuen Hon (2020-04-01). "Suphx: Mastering Mahjong with Deep Reinforcement Learning".
133:
but ended the game after one hand; to maximize its expected score, the AI would have to consider the speed and value of the hand it would like to achieve.
362:
210:
177:
27:
is a relatively complex four-player game with multiple variants played all around the world. When developing a mahjong-related
226:
Xueqing Yan; Yongming Li; Sanjiang Li (2021-08-15). "A Fast
Algorithm for Computing the Deficiency Number of a Mahjong Hand".
77:
195:
RICAI '20: Proceedings of the 2020 2nd
International Conference on Robotics, Intelligent Control and Artificial Intelligence
151:
was able to achieve the second highest rank on Tenhou.net, but was not permitted to play in the highest ranking room.
309:
Kai Jun Chen; Lok Him Lai; Zi Iun Lai (2023-04-06). "A Novel Reward
Shaping Function for Single-Player Mahjong".
28:
262:
98:
331:
310:
227:
206:
173:
357:
198:
47:
110:
adds 300 points to the next winning hand. AI is being developed to do these calculations.
147:
with the intention to make an AI model that could play
Japanese mahjong competitively .
351:
45:
Researchers noticed that the current AI models that existed purely to calculate the
16:
51:
of a hand did not account for the discarded tiles. These researchers developed the
291:
80:; in general, the number of points a hand is worth will be calculated from the
202:
296:
21st
International Conference on Control, Automation and Systems (ICCAS)
193:
Yajun Zheng; Shuqin Li (2020-10-17). "A Review of
Mahjong AI Research".
24:
336:
315:
232:
119:
real life instead of on a computer, some tiles were misidentified.
15:
290:
Takuma Kano; Liang Li; Nak Yong Ko; Woong Choi (2021-10-15).
63:, tiles that are all used or discarded, into account.
172:(1st ed.). Singapore: Tuttle. p. 11.
8:
335:
314:
231:
292:"Calculation of Mahjong Score using AI"
160:
7:
14:
55:, an AI that would calculate the
106:must also be considered; each
1:
114:Recognizing the score with AI
363:Game artificial intelligence
270:European Mahjong Association
263:"Rules for Japanese Mahjong"
379:
203:10.1145/3438872.3439104
29:artificial intelligence
170:The Great Mahjong Book
143:Researchers developed
53:Block Deficiency Model
21:
20:A Japanese mahjong set
247:Chiba, Daina (2020).
128:Single-player mahjong
78:complex scoring rules
76:Japanese mahjong has
19:
197:. pp. 345–349.
168:Rep, Jelte (2007).
59:of the hand taking
22:
212:978-1-4503-8830-6
179:978-0-8048-3719-4
370:
342:
341:
339:
327:
321:
320:
318:
306:
300:
299:
287:
281:
280:
278:
277:
267:
259:
253:
252:
244:
238:
237:
235:
223:
217:
216:
190:
184:
183:
165:
378:
377:
373:
372:
371:
369:
368:
367:
348:
347:
346:
345:
329:
328:
324:
308:
307:
303:
289:
288:
284:
275:
273:
265:
261:
260:
256:
246:
245:
241:
225:
224:
220:
213:
192:
191:
187:
180:
167:
166:
162:
157:
141:
130:
125:
123:Playing mahjong
116:
92:is gained from
74:
69:
43:
12:
11:
5:
376:
374:
366:
365:
360:
350:
349:
344:
343:
322:
301:
282:
254:
251:. p. 198.
239:
218:
211:
185:
178:
159:
158:
156:
153:
140:
135:
129:
126:
124:
121:
115:
112:
73:
70:
68:
65:
42:
33:
13:
10:
9:
6:
4:
3:
2:
375:
364:
361:
359:
356:
355:
353:
338:
333:
326:
323:
317:
312:
305:
302:
297:
293:
286:
283:
271:
264:
258:
255:
250:
249:Riichi Book 1
243:
240:
234:
229:
222:
219:
214:
208:
204:
200:
196:
189:
186:
181:
175:
171:
164:
161:
154:
152:
150:
146:
139:
136:
134:
127:
122:
120:
113:
111:
109:
105:
101:
100:
95:
91:
88:of the hand.
87:
83:
79:
72:Scoring rules
71:
66:
64:
62:
58:
54:
50:
49:
41:
37:
34:
32:
30:
26:
18:
325:
304:
295:
285:
274:. Retrieved
272:. 2016-04-01
269:
257:
248:
242:
221:
194:
188:
169:
163:
148:
144:
142:
137:
131:
117:
107:
103:
97:
93:
89:
85:
81:
75:
60:
56:
52:
46:
44:
39:
35:
23:
352:Categories
337:2003.13590
316:2305.04145
276:2023-09-21
233:2108.06832
155:References
358:Mahjong
67:Scoring
57:shanten
48:shanten
36:Shanten
25:Mahjong
209:
176:
332:arXiv
311:arXiv
266:(PDF)
228:arXiv
149:Suphx
145:Suphx
138:Suphx
108:honba
104:Honba
207:ISBN
174:ISBN
99:yaku
96:and
94:dora
84:and
61:Kabe
40:kabe
38:and
199:doi
90:Han
86:han
354::
294:.
268:.
205:.
102:.
82:fu
340:.
334::
319:.
313::
298:.
279:.
236:.
230::
215:.
201::
182:.
Text is available under the Creative Commons Attribution-ShareAlike License. Additional terms may apply.
