-
Notifications
You must be signed in to change notification settings - Fork 0
/
mcms-bnaic.bib
executable file
·1568 lines (1374 loc) · 48.9 KB
/
mcms-bnaic.bib
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
412
413
414
415
416
417
418
419
420
421
422
423
424
425
426
427
428
429
430
431
432
433
434
435
436
437
438
439
440
441
442
443
444
445
446
447
448
449
450
451
452
453
454
455
456
457
458
459
460
461
462
463
464
465
466
467
468
469
470
471
472
473
474
475
476
477
478
479
480
481
482
483
484
485
486
487
488
489
490
491
492
493
494
495
496
497
498
499
500
501
502
503
504
505
506
507
508
509
510
511
512
513
514
515
516
517
518
519
520
521
522
523
524
525
526
527
528
529
530
531
532
533
534
535
536
537
538
539
540
541
542
543
544
545
546
547
548
549
550
551
552
553
554
555
556
557
558
559
560
561
562
563
564
565
566
567
568
569
570
571
572
573
574
575
576
577
578
579
580
581
582
583
584
585
586
587
588
589
590
591
592
593
594
595
596
597
598
599
600
601
602
603
604
605
606
607
608
609
610
611
612
613
614
615
616
617
618
619
620
621
622
623
624
625
626
627
628
629
630
631
632
633
634
635
636
637
638
639
640
641
642
643
644
645
646
647
648
649
650
651
652
653
654
655
656
657
658
659
660
661
662
663
664
665
666
667
668
669
670
671
672
673
674
675
676
677
678
679
680
681
682
683
684
685
686
687
688
689
690
691
692
693
694
695
696
697
698
699
700
701
702
703
704
705
706
707
708
709
710
711
712
713
714
715
716
717
718
719
720
721
722
723
724
725
726
727
728
729
730
731
732
733
734
735
736
737
738
739
740
741
742
743
744
745
746
747
748
749
750
751
752
753
754
755
756
757
758
759
760
761
762
763
764
765
766
767
768
769
770
771
772
773
774
775
776
777
778
779
780
781
782
783
784
785
786
787
788
789
790
791
792
793
794
795
796
797
798
799
800
801
802
803
804
805
806
807
808
809
810
811
812
813
814
815
816
817
818
819
820
821
822
823
824
825
826
827
828
829
830
831
832
833
834
835
836
837
838
839
840
841
842
843
844
845
846
847
848
849
850
851
852
853
854
855
856
857
858
859
860
861
862
863
864
865
866
867
868
869
870
871
872
873
874
875
876
877
878
879
880
881
882
883
884
885
886
887
888
889
890
891
892
893
894
895
896
897
898
899
900
901
902
903
904
905
906
907
908
909
910
911
912
913
914
915
916
917
918
919
920
921
922
923
924
925
926
927
928
929
930
931
932
933
934
935
936
937
938
939
940
941
942
943
944
945
946
947
948
949
950
951
952
953
954
955
956
957
958
959
960
961
962
963
964
965
966
967
968
969
970
971
972
973
974
975
976
977
978
979
980
981
982
983
984
985
986
987
988
989
990
991
992
993
994
995
996
997
998
999
1000
@incollection{veness2011,
title ={Variance Reduction in {Monte-Carlo Tree Search}},
author={J. Veness and M. Lanctot and M. Bowling},
booktitle = {Advances in Neural Information Processing Systems 24},
editor = {J. Shawe-Taylor and R.S. Zemel and P. Bartlett and F.C.N. Pereira and K.Q. Weinberger},
pages = {1836--1844},
year = {2011}
}
@inproceedings{Lanctot12sparse,
author = {M. Lanctot and A. Saffidine and J. Veness and C. Archibald},
title = {Sparse Sampling for Adversarial Games},
booktitle = {Proceedings of Computer Games Worksop, {ECAI 2012}},
year = 2012
}
@article{Lanctot13MCMS-TR,
author = {M. Lanctot and A. Saffidine and J. Veness and C. Archibald and M.H.M. Winands},
title = {Monte Carlo *-Minimax Search},
journal = {CoRR},
year = 2013,
volume = {abs/1304.6057},
note = {\url{http://arxiv.org/abs/1304.6057}},
ee = {http://arxiv.org/abs/1304.6057},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{hoeffding1963,
title = {Probability Inequalities for Sums of Bounded Random Variables},
author = {Hoeffding, Wassily},
journal = {Journal of the American Statistical Association},
volume = {58},
number = {301},
pages = {pp. 13-30},
abstract = {Upper bounds are derived for the probability that the sum S of n independent random variables exceeds its mean ES by a positive number nt. It is assumed that the range of each summand of S is bounded or bounded above. The bounds for <tex-math>$\Pr \{ S - ES \geq nt \}$</tex-math> depend only on the endpoints of the ranges of the summands and the mean, or the mean and the variance of S. These results are then used to obtain analogous inequalities for certain sums of dependent random variables such as U statistics and the sum of a random sample without replacement from a finite population.},
language = {English},
year = {1963},
publisher = {American Statistical Association},
}
@article{fang08retrograde,
author = {H. Fang and J. Glenn and C. Kruskal},
title = {Retrograde approximation algorithms for jeopardy stochastic games},
journal = {{ICGA} journal},
volume = 31,
number = 2,
pages = {77--96},
year = 2008
}
@inproceedings{glenn09generalized,
author = {J. Glenn and C. Aloi},
title = {Optimizing Genetic Algorithm Parameters for a Stochastic Game},
booktitle = {Proceedings of 22nd FLAIRS Conference},
pages = {421--426},
year = {2009},
}
@inproceedings{glenn07retrograde,
author = {J. Glenn and H.-r. Fang and C. Kruskal},
title = {A Retrograde Approximation Algorithm for Two-player {C}an't {S}top},
booktitle = {Proceedings of Computers and Games Workshop},
year = {2007},
}
@inproceedings{glenn:optimizing,
author = "J. Glenn",
title = "Optimizing Genetic Algorithm Parameters for a Stochastic Game",
booktitle = "IJCCI (ICEC)'10",
pages = {199--206},
year = {2010},
}
@article{knuth75, key="knuth75", author="D.E. Knuth and R.W. Moore",
title="An Analysis of Alpha-Beta Pruning",
journal="Artificial Intelligence",
volume= 6,
number = 4,
pages = "293--326",
year=1975}
@inproceedings{schadd2009,
author = "M.P.D. Schadd and M.H.M. Winands and J.W.H.M. Uiterwijk",
title = "{ChanceProbcut}: {F}orward Pruning in Chance Nodes",
booktitle = "2009 IEEE Symposium on Computational Intelligence and Games (CIG'09)",
pages = {178--185},
editor = {P.L. Lanzi},
year = {2009},
}
@techreport{smith1993,
author = {S.J.J. Smith and D.S. Nau},
title = {Toward an Analysis of Forward Pruning},
institution = {University of Maryland at College Park, College
Park},
number = {CS-TR-3096},
year = 1993
}
@inproceedings{Coutoux11a,
title = {Adding Double Progressive Widening to Upper Confidence Trees to Cope With Uncertainty in Planning Problems},
author = {Couetoux, A. and Doghmen, H.},
booktitle={The 9th European Workshop on Reinforcement Learning (EWRL)},
year = {2011},
}
@inproceedings{Coutoux11b,
hal_id = {hal-00542673},
url = {http://hal.archives-ouvertes.fr/hal-00542673},
title = {Continuous Upper Confidence Trees},
author = {Couetoux, A. and Hoock, J-B. and Sokolovska, N. and Teytaud, O. and Bonnard, N.},
abstract = {{Upper Confidence Trees are a very efficient tool for solving Markov Decision Processes; originating in difficult games like the game of Go, it is in particular surprisingly efficient in high dimensional problems. It is known that it can be adapted to continuous domains in some cases (in particular continuous action spaces). We here present an extension of Upper Confidence Trees to continuous stochastic problems. We (i) show a deceptive problem on which the classical Upper Confidence Tree approach does not work, even with arbitrarily large computational power and with progressive widening (ii) propose an improvement, termed double-progressive widening, which takes care of the compromise between variance (we want infinitely many simulations for each action/state) and bias (we want sufficiently many nodes to avoid a bias by the first nodes) and which extends the classical progressive widening (iii) discuss its consistency and show experimentally that it performs well on the deceptive problem and on experimental benchmarks. We guess that the double-progressive widening trick can be used for other algorithms as well, as a general tool for ensuring a good bias/variance compromise in search algorithms.}},
language = {English},
affiliation = {Laboratoire de Recherche en Informatique - LRI , TAO - INRIA Saclay - Ile de France , Chercheur Ind{\'e}pendant},
booktitle = {{LION'11: Proceedings of the 5th International Conference on Learning and Intelligent OptimizatioN}},
address = {Italy},
audience = {international},
year = {2011},
pdf = {http://hal.archives-ouvertes.fr/hal-00542673/PDF/c0mcts.pdf},
}
@inproceedings{Coulom07Efficient,
author = {R. Coulom},
title = {Efficient selectivity and backup operators in {Monte-Carlo} tree search},
booktitle = {Proceedings of the 5th international conference on Computers and games},
year = {2007},
pages = {72--83},
publisher = {Springer-Verlag},
}
@inproceedings{DBLP:conf/lion/CouetouxHSTB11,
author = {A. Cou{\"e}toux and
J-B. Hoock and
N. Sokolovska and
O. Teytaud and
N. Bonnard},
title = {Continuous Upper Confidence Trees},
booktitle = {LION},
year = {2011},
pages = {433-445},
ee = {http://dx.doi.org/10.1007/978-3-642-25566-3_32},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@article{Ballard83,
author = {B.W. Ballard},
title = {The *-Minimax Search Procedure for Trees Containing Chance Nodes},
journal = {Artificial Intelligence},
volume = {21},
number = {3},
year = {1983},
pages = {327--350},
}
@inproceedings{RamanujanS11,
author = {R. Ramanujan and
B. Selman},
title = {Trade-Offs in Sampling-Based Adversarial Planning},
booktitle = {ICAPS},
year = {2011},
ee = {http://aaai.org/ocs/index.php/ICAPS/ICAPS11/paper/view/2708},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{citeulike:7458873,
author = {Ramanujan, R. and Sabharwal, A. and Selman, B.},
booktitle = {Proceedings of Uncertainty in Artificial Intelligence},
citeulike-article-id = {7458873},
keywords = {comparison, empirical, sampling, uct},
posted-at = {2010-07-11 17:09:59},
priority = {4},
title = {{Understanding Sampling Style Adversarial Search Methods}},
year = {2010}
}
@inproceedings{DBLP:conf/aips/RamanujanSS10,
author = {R. Ramanujan and
A. Sabharwal and
B. Selman},
title = {On Adversarial Search Spaces and Sampling-Based Planning},
booktitle = {ICAPS},
year = {2010},
pages = {242-245},
ee = {http://www.aaai.org/ocs/index.php/ICAPS/ICAPS10/paper/view/1458},
crossref = {DBLP:conf/aips/2010},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@book{russellnorvig,
author = {Stuart J. Russell and
Peter Norvig},
title = {Artificial Intelligence - A Modern Approach (3. internat.
ed.)},
publisher = {Pearson Education},
year = {2010},
isbn = {978-0-13-207148-2},
pages = {I-XVIII, 1-1132},
ee = {http://vig.pearsoned.com/store/product/1,1207,store-12521_isbn-0136042597,00.html},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{walsh10,
author = {T.J. Walsh and
S. Goschin and
M.L. Littman},
title = {Integrating Sample-Based Planning and Model-Based Reinforcement
Learning},
booktitle = {AAAI},
year = {2010},
ee = {http://www.aaai.org/ocs/index.php/AAAI/AAAI10/paper/view/1880},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{kocsis06,
author = {L. Kocsis and
C. Szepesv{\'a}ri},
title = {Bandit Based {M}onte-{C}arlo Planning},
booktitle = {ECML},
year = {2006},
pages = {282-293}
}
@MastersThesis{heyden09,
author = {C. Heyden},
title = {{Implementing a Computer Player for Carcassonnne}},
school = {Department of Knowledge Engineering, Maastricht University},
year = {2009}
}
@INPROCEEDINGS{veness07,
author={Veness, J. and Blair, A.},
booktitle={Computational Intelligence and Games, 2007. CIG 2007. IEEE Symposium on},
title={Effective Use of Transposition Tables in Stochastic Game Tree Search},
year={2007},
month={april},
volume={},
number={},
pages={112 -116},
keywords={Ballard Star2 algorithm;alpha-beta searcher;stochastic game tree search;transposition tables;search problems;stochastic games;trees (mathematics);},
doi={10.1109/CIG.2007.368086},
ISSN={},}
@article{chang2005,
author = {Chang, H.S. and Fu, M.C. and Hu, J. and Marcus, S.I.},
keywords = {bandits, forward, greedy, mdps, search, upper-confidence-bound},
month = {January},
number = {1},
pages = {126--139},
posted-at = {2010-08-24 01:45:41},
priority = {0},
title = {An Adaptive Sampling Algorithm for Solving Markov Decision Processes},
volume = {53},
year = {2005},
journal = {Operations Research}
}
@techreport{gelly06,
author = {S. Gelly and Y. Wang and R. Munos and O. Teytaud},
title = {Modification of {UCT} with Patterns in {Monte-Carlo Go}},
institution = {Institut National de Recherche en Informatique et en Automatique ({INRIA})},
number = {RR-6062},
month = {November},
year = 2006
}
@inproceedings{chaslot08,
author = {G. and S. Bakkes and I. Szita and P. Spronck},
title = {Monte-{C}arlo Tree Search: A New Framework for Game AI},
booktitle = {Proceedings of the Fourth Artificial Intelligence and Interactive Digital Entertainment Conference},
publisher = {AAAI Press},
year = 2008
}
@inproceedings{bjornsson08,
author = {H. Finnsson and Y. Bj\"{o}rnsson},
title = {Simulation-Based Approach to General Game Playing},
booktitle = {The Twenty-Third AAAI Conference on Artificial Intelligence},
pages = {259--264},
publisher = {AAAI Press},
year = 2008
}
@article{winands10,
author = {M.H.M. Winands and Y. Bj\"{o}rnsson and J-T. Saito},
title = {{Monte Carlo Tree Search in Lines of Action}},
journal = {{IEEE} Transactions on Computational Intelligence and {AI} in Games},
volume = 2,
number = 4,
pages = {239--250},
year = 2010
}
@article{lee09,
author = {C-S. Lee and M-H. Wang and G. Chaslot and J-B. Hoock and A. Rimmel and O. Teytaud and S-R. Tsai and S-C. Hsu and T-P. Hong},
title = {The Computational Intelligence of {M}o{G}o Revealed in {T}aiwan's Computer {G}o Tournaments},
journal = {{IEEE} Transactions on Computational Intelligence and {AI} in Games},
volume = 1,
number = 1,
pages = {73--89},
year = 2009
}
@inproceedings{szita10,
author = {I. Szita and G. Chaslot and P. Spronck},
title = {{Monte-Carlo Tree Search in Settlers of Catan}},
booktitle = {Proceedings of Advances in Computer Games (ACG 2009)},
pages = {21--34},
year = 2010
}
@article{ciancarini10,
author = {P. Ciancarini and G.P. Favini},
title = {{M}onte {C}arlo tree search in {K}riegspiel},
journal = {Artificial Intelligence},
pages = {670--684},
volume = 174,
number = 11,
year = 2010
}
@inproceedings{auger11,
author = {D. Auger},
title = {Multiple Tree for Partially Observable Monte-Carlo Tree Search},
booktitle = {Proceedings of the 2011 International Conference on Applications of Evolutionary Computation},
year = 2011,
pages = {53--62}
}
@article{mctssurvey,
author={Browne, C.B. and Powley, E. and Whitehouse, D. and Lucas, S.M. and Cowling, P.I. and Rohlfshagen, P. and Tavener, S. and Perez, D. and Samothrakis, S. and Colton, S.},
journal={Computational Intelligence and AI in Games, IEEE Transactions on},
title={A Survey of {M}onte {C}arlo Tree Search Methods},
year={2012},
month={march },
volume={4},
number={1},
pages={1 -43},
keywords={},
doi={10.1109/TCIAIG.2012.2186810},
ISSN={1943-068X},
}
@article{gelly12,
title = {The Grand Challenge of Computer Go: Monte Carlo Tree Search and Extensions},
author = {Sylvain Gelly and Levente Kocsis and Marc Schoenauer and Mich\`{e}le Sebag and David Silver, Csaba Szepesv\'{a}ri and Olivier Teytaud},
journal = {Communications of the {ACM}},
year = 2012,
month = March,
volume = 55,
number = 3,
pages = {106--113}
}
@inproceedings{mcgammon,
author = {Francois Van Lishout and Guillaume Chaslot and Jos W.H.M. Uiterwijk},
title = {Monte-Carlo Tree Search in Backgammon},
booktitle = {Proceedings of the Computer Games Workshop},
year = 2007,
pages = {175--184}
}
@book{bertsekas1996,
author = {Bertsekas, Dimitri P. and Tsitsiklis, John N.},
title = {Neuro-Dynamic Programming},
year = {1996},
isbn = {1886529108},
edition = {1st},
publisher = {Athena Scientific},
}
@article{pig,
title = {Scarne on {D}ice},
author = {J. Scarne},
journal = {Harrisburg, PA: Military Service Publishing Co},
year = {1945},
}
% Computing "Elo Ratings" of Move Patterns in the Game of Go. ICGA Journal 30(4): 198-208 (2007).
@article{Coulom07Computing,
title = {Computing ``{ELO} Ratings'' of Move Patterns in the game of {G}o},
author = {R. Coulom},
journal = {ICGA Journal},
volume = 30,
number = 4,
pages = {198--208},
year = 2007
}
@Book{Russell2003,
AUTHOR = {Stuart Russell and Peter Norvig},
TITLE = {Artificial Intelligence: A Modern Approach},
PUBLISHER = {Prentice-Hall, Englewood Cliffs, NJ},
YEAR = {2003},
EDITION = {2nd edition}
}
@inproceedings{silver09b,
author = {David Silver and
Gerald Tesauro},
title = {{Monte-Carlo simulation balancing}},
booktitle = {ICML},
year = {2009},
pages = {119},
ee = {http://doi.acm.org/10.1145/1553374.1553495},
bibsource = {DBLP, http://dblp.uni-trier.de}
}
@inproceedings{silver10,
title = {{Monte-Carlo Planning in Large POMDPs}},
author = {D. Silver and J. Veness},
booktitle = {Advances in Neural Information Processing Systems 23},
pages = {2164--2172},
year = {2010}
}
@article{bertsekas99,
author = {Bertsekas, Dimitri P. and Castanon, David A.},
title = {Rollout Algorithms for Stochastic Scheduling Problems},
journal = {Journal of Heuristics},
volume = {5},
number = {1},
year = {1999},
issn = {1381-1231},
pages = {89--108},
doi = {http://dx.doi.org/10.1023/A:1009634810396},
publisher = {Kluwer Academic Publishers},
address = {Hingham, MA, USA},
}
@InProceedings(09ijcai-mivat,
Title = "Learning a Value Analysis Tool For Agent Evaluation",
Author = "Martha White and Michael Bowling",
Booktitle = "Proceedings of the Twenty-First International Joint Conference on Artificial Intelligence (IJCAI)",
Year = "2009",
Pages = "1976--1981",
AcceptRate = "26\%",
AcceptNumbers = "331 of 1290"
)
@book{ross-simul,
title = "Simulation",
author = "Sheldon M. Ross",
publisher = "Academic Press",
address = "San Diego",
year = "2006",
edition = "4th"
}
@inproceedings{lec1994,
author = {L'Ecuyer, Pierre},
title = {Efficiency improvement and variance reduction},
booktitle = {Proceedings of the 26th conference on Winter simulation},
series = {WSC '94},
year = {1994},
isbn = {0-7803-2109-X},
location = {Orlando, Florida, United States},
pages = {122--132},
numpages = {11},
url = {http://portal.acm.org/citation.cfm?id=193201.193994},
acmid = {193994},
publisher = {Society for Computer Simulation International},
address = {San Diego, CA, USA},
}
@article{nelson1990,
jstor_articletype = {research-article},
title = {Control Variate Remedies},
author = {Nelson, Barry L.},
journal = {Operations Research},
jstor_issuetitle = {},
volume = {38},
number = {6},
jstor_formatteddate = {Nov. - Dec., 1990},
pages = {pp. 974-992},
url = {http://www.jstor.org/stable/170965},
ISSN = {0030364X},
abstract = {Other than common random numbers, control variates is the most promising variance reduction technique in terms of its potential for widespread use: Control variates is applicable in single or multiple response simulation, it does not require altering the simulation run in any way, and any stochastic simulation contains potential control variates. A rich theory of control variates has been developed in recent years. Most of this theory assumes a specific probabilistic structure for the simulation output process, usually joint normality of the response and the control variates. When these assumptions are not satisfied, desirable properties of the estimator, such as unbiasedness, may be lost. A number of remedies for violations of the assumptions have been proposed, including jackknifing and splitting. However, there has been no systematic analytical and empirical evaluation of these remedies. This paper presents such an evaluation, including evaluation of the small-sample statistical properties of the proposed remedies.},
language = {English},
year = {1990},
publisher = {INFORMS},
copyright = {Copyright © 1990 INFORMS},
}
@article{neller10,
author = {T.W. Neller and C.G.M. Presser},
title = {Practical Play of the Dice Game {P}ig},
journal = {Undergraduate Mathematics and Its Applications},
volume = {26},
number = {4},
year = {2010},
pages = {443--458}
}
@article{neller04,
author = {Todd W. Neller and Clifton G.M. Pressor},
title = {Optimal Play of the Dice Game Pig},
journal = {Undergraduate Mathematics and Its Applications},
volume = {25},
number = {1},
year = {2004},
pages = {25--47}
}
@article{dominion,
title = {Dominion},
author = {Donald X. Vaccarino},
journal = {Rio Grande Games},
year = {2008},
}
@article{cantstop,
title = {{C}an't {S}top},
author = {S. Sackson},
journal = {Ravensburger},
year = {1980},
}
@article{antos10,
author = {Antos, Andr\'{a}s and Grover, Varun and Szepesv\'{a}ri, Csaba},
title = {Active learning in heteroscedastic noise},
journal = {Theoretical Computer Science},
volume = {411},
number = {29-30},
year = {2010},
issn = {0304-3975},
pages = {2712--2728},
doi = {http://dx.doi.org/10.1016/j.tcs.2010.04.007},
publisher = {Elsevier Science Publishers Ltd.},
address = {Essex, UK},
}
@MISC{csaba09reinforcementlearning,
author = {Csaba Szepesv\'{a}ri},
title = {Reinforcement Learning Algorithms for {MDPs}},
year = {2009}
}
@article {Veness:arXiv0909.0801,
author={Joel Veness and Kee Siong Ng and Marcus Hutter and David Silver},
title={A {M}onte {C}arlo {AIXI} {A}pproximation},
year="2009",
journal="CoRR",
volume="abs/0909.0801",
doi=""
}
@inproceedings{pascal08,
author = {Pascal Poupart and Nikos Vlassis},
title = "Model-based {B}ayesian {R}einforcement {L}earning in {P}artially {O}bservable {D}omains",
booktitle = "ISAIM",
year = 2008
}
@inproceedings{hoehn05,
author = {Hoehn, Bret and Southey, Finnegan and Holte, Robert C. and Bulitko, Valeriy},
title = {Effective short-term opponent exploitation in simplified poker},
booktitle = {AAAI'05},
year = {2005},
pages = {783--788}
}
@Book{ cesa-bianchi,
author = {N. Cesa-Bianchi and G. Lugosi},
title = {Prediction, Learning, and Games},
publisher = {CUP},
year = {2006}
}
@inproceedings{strens00,
author = "M. Strens",
title = "A {B}ayesian framework for reinforcement learning",
booktitle = "ICML",
year = "2000",
pages = "943-950"
}
@article{ veness09,
author = {Veness, Joel and Silver, David and Uther, William and Blair, Alan},
title = "Bootstrapping from Game Tree Search",
journal = "NIPS",
year = "2009",
note = "To appear"
}
@inproceedings{wang05,
author = {T. Wang and
D.J. Lizotte and
M.H. Bowling and
D. Schuurmans},
title = {Bayesian sparse sampling for on-line reward optimization},
booktitle = {ICML},
year = {2005},
pages = {956-963},
}
@article{hutter07topdown,
author = {Marcus Hutter},
title = {Universal Algorithmic Intelligence: A mathematical top-$>$down
approach},
journal = {CoRR},
volume = {abs/cs/0701125},
year = {2007}
}
@inproceedings{hutter02,
author = {Marcus Hutter},
title = {Self-Optimizing and Pareto-Optimal Policies in General Environments
Based on Bayes-Mixtures},
booktitle = {COLT},
year = {2002},
pages = {364-379}
}
@Book{ sipser05,
author = {Michael Sipser},
title = {Introduction to the Theory of Computation},
publisher = {Course Technology},
year = {2005},
edition = {2nd}
}
@Book{ boolos02,
author = {George S. Boolos and John P. Burgess and Richard C. Jeffrey},
title = {Computability and Logic},
publisher = {Cambridge University Press},
year = {2002},
edition = {4th}
}
@PhdThesis{ LeggPHD08,
author = {Shane Legg},
title = {Machine Super Intelligence},
school = {Department of Informatics, University of Lugano},
year = {2008}
}
@inproceedings{makino09,
author = {Makino, Takaki},
title = {Proto-predictive representation of states with simple recurrent temporal-difference networks},
booktitle = {ICML},
year = {2009},
isbn = {978-1-60558-516-1},
pages = {697--704}
}
@article{Willems94ctwext,
author = {Frans M. J. Willems},
title = {The Context-Tree Weighting Method: Extensions},
journal = {IEEE Transactions on Information Theory},
year = {1998},
volume = {44},
pages = {792--798}
}
@book{ wallace05,
author = "C.S. Wallace",
title = "Statistical and Inductive Inference by Minimum Message Length",
publisher = "Springer",
year = 2005
}
@inproceedings{SuttonT04,
author = {Richard S. Sutton and
Brian Tanner},
title = {Temporal-Difference Networks},
booktitle = {NIPS},
year = {2004}
}
@inproceedings{gelly07,
Author = {S. Gelly and D. Silver},
Title = {Combining Online and Offline Learning in {UCT}},
Booktitle = {Proceedings of the 17th International Conference on Machine Learning},
Year = {2007},
Pages = {273-280}
}
@INPROCEEDINGS{chrisman92,
author = {Lonnie Chrisman},
title = {Reinforcement Learning with Perceptual Aliasing: The Perceptual Distinctions Approach},
booktitle = {Proceedings of the Tenth National Conference on Artificial Intelligence},
year = {1992},
pages = {183--188}
}
@book{ li-vitanyi,
author = "Ming Li and Paul Vit{\'a}nyi",
title = "An Introduction to Kolmogorov Complexity and Its Applications",
year = 2008,
publisher = "Springer"
}
@article{ kt-estimator,
author = "R.E. Krichevsky and V.K. Trofimov",
title = "The performance of universal coding",
journal = "IEEE Transactions on Information Theory",
volume = "IT-27",
pages = "199-207",
year = 1981
}
@article{farias07,
author = {V. Farias and
C. Moallemi and
T. Weissman and
B. Van Roy},
title = {Universal {R}einforcement {L}earning},
journal = {CoRR},
volume = {abs/0707.3087},
year = {2007}
}
@article{farias09b,
author = {Farias, Vivek F. and Moallemi, Ciamac C. and Weissman, Tsachy and Van Roy, Benjamin},
title = "Universal Reinforcement Learning",
journal = "IEEE Transactions on Information Theory",
year = "2009",
note = "To appear"
}
@inproceedings{kearns99,
author = "M.J. Kearns and Y. Mansour and A.Y. Ng",
title = "A sparse sampling algorithm for near-optimal planning in
large {M}arkov {D}ecision {P}rocesses",
booktitle = {IJCAI},
pages = "1324-1331",
year = 1999
}
@inproceedings{ psr04,
author = "Satinder Singh and Michael James and Matthew Rudary",
title = "Predictive state representations: {A} new theory for modeling dynamical systems",
booktitle = "UAI",
pages = "512-519",
year = 2004
}
@inproceedings{ psr02,
author = "Michael Littman and Richard Sutton and Satinder Singh",
title = "Predictive representations of state",
booktitle = "NIPS",
pages = "1555-1561",
year = 2002
}
@article{ lempel-ziv77,
author = "Jacob Ziv and Abraham Lempel",
title = "A universal algorithm for sequential data compression",
journal = "IEEE Transactions on Information Theory",
volume = "23",
number = 3,
pages = "337-343",
year = 1977
}
@inproceedings{ shani04,
author = "Guy Shani and Ronen Brafman",
title = "Resolving perceptual aliasing in the presence of noisy sensors",
booktitle = "NIPS",
year = 2004
}
@PhdThesis{ shani07,
author = {Guy Shani},
title = {Learning and Solving Partially Observable Markov
Decision Processes},
school = {Ben-Gurion University of the Negev},
year = {2007}
}
@article{ watkins92,
author = "Christopher Watkins and Peter Dayan",
title = "Q-learning",
journal = "Machine Learning",
volume = 8,
pages = "279-292",
year = 1992
}
@inproceedings{ volf95,
author = "Paul A.J. Volf and Frans M.J. Willems",
title = "A Study of the Context Tree Maximizing Method",
booktitle = "16th Symposium on Information Theory in the Benelux",
pages = "3-9",
year = 1995
}
@inproceedings{ suematsu99,
author = "Nobuo Suematsu and Akira Hayashi",
title = "A reinforcement learning algorithm in partially observable
environments using short-term memory",
booktitle = "NIPS",
pages = "1059-1065",
year = 1999
}
@inproceedings{ suematsu97,
author = "Nobuo Suematsu and Akira Hayashi and Shigang Li",
title = "A {B}ayesian approach to model learning in non-{M}arkovian environment",
booktitle = "ICML",
pages = "349-357",
year = "1997"
}
@inproceedings{Ponsen10a,
title = {{Integrating Opponent Models with Monte-Carlo Tree Search in Poker}},
author = {Marc Ponsen and Geert Gerritsen and Guillaume Chaslot},
booktitle = {Proceedings of {Interactive Decision Theory and Game Theory} Workshop at the Twenty-Fourth Conference on Artificial Intelligence (AAAI-10)},
publisher = {AAAI press},
year = {2010},
}
@inproceedings{BjarnasonFT09,
author = {Ronald Bjarnason and
Alan Fern and
Prasad Tadepalli},
title = {{Lower Bounding Klondike Solitaire with Monte-Carlo Planning}},
booktitle = {ICAPS},
year = {2009},
}
@inproceedings{BallaF09,
author = {Radha-Krishna Balla and
Alan Fern},
title = {{UCT for Tactical Assault Planning in Real-Time Strategy
Games}},
booktitle = {IJCAI},
year = {2009},
pages = {40-45},
}
@inproceedings{Finnsson08,
author = {Hilmar Finnsson and Yngvi Bjornsson},
title = {{Simulation-based Approach to General Game Playing}},
booktitle = {Twenty-Third AAAI Conference on Artificial Intelligence (AAAI 2008)},
pages = {259--264},
year = 2008
}
@article{mueller09,
author = {David Tom and Martin Mueller},
title = {{A Study of UCT and Its Enhancements in an Artificial Game}},
journal = {Lecture Notes in Computer Science},
volume = {6048/2010},
year = 2010,
pages = {55--64}
}
@inproceedings{chaslot08mcts,
title = {Monte-Carlo Tree Search: A New Framework for Game {AI}},
author = {G. Chaslot and S. Bakkes and I. Szita and P. Spronck},
booktitle = {Fourth Artificial Intelligence and Interactive Digital Entertainment Conference (AIIDE 2008)},
year = 2008
}
@article{chaslot08cem-mcts,
title = {{Cross-entropy for Monte-Carlo Tree Search}},
author = {Guillaume M.J-B. Chaslot and Mark H.M. Winands and Istvan Szita and H. Jaap van den Herik},
journal = {{ICGA}},
volume = 31,
number = 3,
pages = {145--156},
year = {2008}
}
@inproceedings{chaslot08,
author = {Chaslot, Guillaume M. and Winands, Mark H. and Herik, H. Jaap},
title = {{Parallel Monte-Carlo Tree Search}},
booktitle = {Proceedings of the 6th International Conference on Computers and Games},
year = {2008},
isbn = {978-3-540-87607-6},
pages = {60--71},
location = {Beijing, China},
doi = {http://dx.doi.org/10.1007/978-3-540-87608-3_6},
publisher = {Springer-Verlag},
address = {Berlin, Heidelberg},
}
@article{ChaslotWHUB2008,
title = {Progressive strategies for Monte-Carlo Tree Search},
author = {G.M.J-B. Chaslot and M.H.M. Winands and H.J. van den Herik and J.W.H.M. Uiterwijk and B. Bouzy},
journal = {New Mathematics and Natural Computation},
volume = {4},
number = {3},
pages = {343--357},
year = {2008},
publisher = {World Scientific Publishing Company}
}
@techreport{gelly2006tr,
abstract = {Algorithm UCB1 for multi-armed bandit problem has already been extended to Algorithm UCT (Upper bound Confidence for Tree) which works for minimax tree search. We have developed a Monte-Carlo Go program, MoGo, which is the first computer Go program using UCT. We explain our modification of UCT for Go application and also the intelligent random simulation with patterns which has improved significantly the performance of MoGo. UCT combined with pruning techniques for large Go board is discussed, as well as parallelization of UCT. MoGo is now a top level Go program on 9x9 and 13x13 Go boards.},
author = {Gelly, Sylvain and Wang, Yizao and Munos, R\'{e}mi and Teytaud, Olivier},
citeulike-article-id = {2990556},
citeulike-linkout-0 = {http://hal.inria.fr/docs/00/12/15/16/PDF/RR-6062.pdf},
institution = {INRIA, France},
keywords = {computer-go, mogo, monte-carlo, ucb1, uct},
month = {November},
number = {6062},
posted-at = {2008-07-11 21:02:49},
priority = {2},
title = {Modification of {UCT} with Patterns in {M}onte-{C}arlo {G}o},
url = {http://hal.inria.fr/docs/00/12/15/16/PDF/RR-6062.pdf},
year = {2006}
}
@Article{ legg07,
author = {Shane Legg and Marcus Hutter},
title = {Universal Intelligence: A Definition of Machine Intelligence},
journal = {Minds and Machines},
year = {2007},
volume = {17},
number = {4},
pages = {391-444}
}
@Book{ sutton-barto98,
author = {Richard S. Sutton and Andrew G. Barto},
title = {Reinforcement Learning: An Introduction},
publisher = {MIT Press},
year = {1998}
}
@Unpublished{ uther09,
author = {William Uther},
title = {An Ontology of Partially Observable Reinforcement Learning
Methods},
note = {NICTA Tech report},
year = {2009}
}
@Article{ pereira99,
author = {Fernando C. Pereira and Yoram Singer},
title = {An efficient extension to mixture techniques for
prediction and decision trees},
journal = {Machine Learning},
year = {1999},
volume = {36},
number = {3},
pages = {183-199}
}
@book{ breiman84classification,
author = "Leo Breiman and Jerome Friedman and Richard Olshen and
Charles Stone",
title = "Classification and Regression Trees",
publisher = "Chapman \& Hall",
year = "1984"
}
@article{ freund97decision-theoretic,
author = "Yoav Freund and Robert E. Schapire",
title = "A decision-theoretic generalization of on-line learning and an
application to boosting",
journal = "Journal of Computer and System Sciences",
volume = "55",
number = "1",
pages = "119--139",
year = "1997"
}
@book{ cesa-bianchi06,
author = "Nicol{\`o} Cesa-Bianchi and Gabor Lugosi",
title = "Prediction, Learning, and Games",
publisher = "Cambridge University Press",
year = 2006
}
@Article{ littlestone94,
author = {Nick Littlestone and Manfred K. Warmuth},
title = {The weighted majority algorithm},
journal = {Information and Computation},
year = {1994},
volume = {108},
pages = {212-261}
}
@article{ littlestone88,
author = "Nick Littlestone",
title = "Learning quickly when irrelevant attributes abound: A new
linear-threshold algorithm",
journal = "Machine Learning",