AlphaZero-Style MCTS Training Metrics (212 Iterations)

Policy and value loss, game outcomes, and MCTS search metrics across 212 training iterations of a reinforcement learning agent.
# iteration
loss_policy_train
loss_value_train
loss_policy_val
loss_value_val
gradient_steps
game_length_avg
game_length_stddev
game_length_min
game_length_max
game_wins
game_losses
game_draws
policy_entropy_avg
policy_max_prob_avg
policy_entropy_high_branch_avg
policy_max_prob_high_branch_avg
policy_agreement_avg
value_z_avg
value_q_avg
value_z_stddev
value_q_stddev
value_correction_avg
value_q_spread_avg
value_error_early_avg
value_error_late_avg
value_network_stddev
bench_wins
bench_losses
bench_draws
lr
q_weight
mcts_sims
replay_samples
samples_iter
time_selfplay_secs
time_train_secs
time_bench_secs
1 1 2.327967 0.609146 2.130198 0.453668 0 35.346154 8.750554 21 61 31 21 0 3.360469 0.351662 3.346265 0.355345 0.0 0.204905 0.273133 0.159954 0.180095 0.068228 0.12843 0.345797 0.461009 0.250654 0 0 0 0.0 0.5 160 0 1040 0.048102 0.042645 0.0
2 2 1.606905 0.325328 1.606905 0.325328 16 23.205128 8.673227 11 53 15 24 0 3.315432 0.381771 3.289904 0.390245 0.0 -0.003475 0.112275 0.192878 0.183558 0.11575 0.160829 0.529726 0.383283 0.284155 0 0 0 0.01 0.5 160 512 2340 0.070821 0.079022 0.0
3 3 1.541961 0.290396 1.530454 0.386929 32 22.073171 7.637653 9 47 18 23 0 3.16195 0.398679 3.101594 0.416763 0.0 -0.020227 0.235214 0.150921 0.143491 0.255441 0.140288 0.44093 0.397361 0.244765 0 0 0 0.009571 0.5 160 1024 3620 0.095094 0.099463 0.0
4 4 1.432155 0.273344 1.422725 0.31765 48 19.636364 6.882892 9 40 16 17 0 3.036929 0.454267 2.910229 0.500777 0.0 -0.0073 0.291495 0.183501 0.184854 0.298795 0.174848 0.463655 0.338232 0.268774 0 0 0 0.009143 0.5 160 1536 4900 0.119287 0.121913 0.0
5 5 1.308027 0.209352 1.275144 0.208751 64 20.0 7.620703 9 39 16 14 0 2.888374 0.509189 2.629733 0.635058 0.0 0.000282 0.427307 0.188264 0.173252 0.427025 0.168469 0.423359 0.271056 0.293904 0 0 0 0.008714 0.5 160 2048 6180 0.131988 0.140155 0.0
6 6 1.198525 0.144336 1.213465 0.246567 80 21.089744 6.532786 11 39 18 21 0 2.657458 0.595734 2.356451 0.704983 0.0 -0.018122 0.490517 0.169018 0.161032 0.508639 0.157064 0.333477 0.287152 0.279885 0 0 0 0.008286 0.5 160 2560 7460 0.140118 0.157321 0.0
7 7 1.095408 0.116362 1.102306 0.173412 96 21.666667 6.710467 11 40 21 15 0 2.46193 0.653733 2.11567 0.791154 0.0 -0.001777 0.562294 0.172699 0.146024 0.564071 0.154079 0.311202 0.255981 0.281893 0 0 0 0.007857 0.5 160 3072 8740 0.15012 0.176245 0.0
8 8 0.99392 0.123094 0.985185 0.154978 112 20.459459 7.277022 9 41 16 21 0 2.232462 0.719065 1.810536 0.867272 0.0 -0.015435 0.65089 0.172436 0.130064 0.666325 0.149478 0.280769 0.269729 0.288768 0 0 0 0.007429 0.5 160 3584 10020 0.159759 0.188544 0.0
9 9 0.928725 0.115207 0.947158 0.166903 128 23.688889 6.711168 11 39 29 16 0 2.103519 0.747836 1.693168 0.892193 0.0 0.005865 0.726291 0.153202 0.12438 0.720426 0.145894 0.270764 0.286245 0.293159 0 0 0 0.007 0.5 160 4096 11300 0.174395 0.200691 0.0
10 10 0.861992 0.103936 0.835821 0.121863 144 20.926829 6.266019 10 40 15 26 0 1.952904 0.782877 1.499873 0.935428 0.0 -0.022848 0.782114 0.166414 0.111959 0.804962 0.1343 0.264314 0.205285 0.292495 0 0 0 0.006571 0.5 160 4608 12580 0.191581 0.211236 0.0
11 11 0.768792 0.098531 0.746399 0.100367 160 24.166667 7.201774 9 45 35 13 0 1.786378 0.811289 1.315022 0.962498 0.0 0.005439 0.829095 0.167759 0.094254 0.823656 0.128899 0.210112 0.18415 0.279677 0 0 0 0.006143 0.5 160 5120 13860 0.208913 0.221519 0.0
12 12 0.710774 0.082346 0.695296 0.101216 176 25.693878 7.300099 11 42 38 11 0 1.680123 0.83246 1.193371 0.974586 0.0 -0.017213 0.885491 0.158215 0.085416 0.902704 0.124888 0.176868 0.203686 0.280433 0 0 0 0.005714 0.5 160 5632 15140 0.227589 0.231419 0.0
13 13 0.690287 0.095091 0.664975 0.083302 192 24.020408 6.593529 11 38 27 22 0 1.610231 0.842556 1.100292 0.978649 0.0 0.003546 0.905763 0.150788 0.079446 0.902217 0.121263 0.191118 0.166848 0.273456 0 0 0 0.005286 0.5 160 6144 16420 0.244956 0.242881 0.0
14 14 0.633632 0.079691 0.653496 0.087176 208 23.921569 6.031914 10 42 29 22 0 1.536182 0.855817 0.99487 0.982431 0.0 -0.007951 0.957157 0.149506 0.073988 0.965108 0.118564 0.180897 0.175853 0.265784 0 0 0 0.004857 0.5 160 6656 17700 0.259301 0.253324 0.0
15 15 0.598354 0.079168 0.621055 0.084681 224 27.6 7.124605 11 47 42 18 0 1.474809 0.865286 0.925296 0.986584 0.0 -0.003483 0.973564 0.145857 0.069072 0.977047 0.116657 0.159719 0.165879 0.257336 0 0 0 0.004429 0.5 160 7168 18980 0.272338 0.262661 0.0
16 16 0.594107 0.073667 0.582028 0.078728 240 27.980392 8.217563 10 55 46 15 0 1.409707 0.877057 0.857621 0.988659 0.0 0.002861 0.978227 0.138181 0.062667 0.975366 0.108207 0.132985 0.155372 0.24812 0 0 0 0.004 0.5 160 7680 20260 0.28681 0.273441 0.0
17 17 0.565395 0.071845 0.558806 0.084301 256 24.27907 6.64174 11 41 28 15 0 1.347229 0.886778 0.793835 0.99015 0.0 -0.019673 1.019289 0.151412 0.05817 1.038962 0.112172 0.154742 0.144653 0.25798 0 0 0 0.003571 0.5 160 8192 21540 0.304214 0.283704 0.0
18 18 0.549734 0.072769 0.565281 0.079124 272 26.470588 7.351598 11 48 37 14 0 1.298026 0.893672 0.733402 0.991637 0.0 -0.015192 1.025437 0.146072 0.05465 1.04063 0.1093 0.142202 0.16314 0.248131 0 0 0 0.003143 0.5 160 8704 22820 0.318834 0.292967 0.0
19 19 0.513067 0.074532 0.537855 0.087764 288 26.833333 6.68971 11 45 40 11 0 1.254458 0.900639 0.675129 0.992828 0.0 -0.012567 1.046681 0.139863 0.051698 1.059248 0.106278 0.129554 0.175529 0.23844 0 0 0 0.002714 0.5 160 9216 24100 0.335672 0.302739 0.0
20 20 0.477078 0.0666 0.518919 0.087496 304 26.105263 7.049512 11 47 36 21 0 1.208076 0.907268 0.617117 0.993988 0.0 0.012727 1.067013 0.145635 0.048918 1.054286 0.102608 0.107303 0.165839 0.245584 0 0 0 0.002286 0.5 160 9728 25380 0.352526 0.314191 0.0
21 21 0.459349 0.070144 0.488304 0.085584 320 28.211538 7.25362 12 49 45 7 0 1.172707 0.912395 0.575778 0.994701 0.0 -0.008584 1.090587 0.150403 0.046851 1.099171 0.101292 0.119451 0.175399 0.251985 0 0 0 0.001857 0.5 160 10240 26660 0.369962 0.325691 0.0
22 22 0.437174 0.06595 0.470921 0.0754 336 27.96 6.56661 12 48 41 9 0 1.147808 0.916909 0.546021 0.995111 0.0 -0.010805 1.103641 0.137594 0.044565 1.114445 0.096813 0.097577 0.146554 0.237995 0 0 0 0.001429 0.5 160 10752 27940 0.386353 0.33617 0.0
23 23 0.42048 0.066155 0.438165 0.068509 352 29.627451 7.518196 12 50 56 12 0 1.113977 0.922372 0.505369 0.995625 0.0 -0.000883 1.116255 0.138552 0.042197 1.117138 0.091468 0.102217 0.133453 0.238731 0 0 0 0.001 0.5 160 11264 29220 0.402997 0.347068 0.0
24 24 0.399363 0.066915 0.433586 0.069024 368 28.796296 7.53299 11 50 50 14 0 1.086256 0.926145 0.473541 0.995941 0.0 -0.006602 1.132143 0.140865 0.040307 1.138745 0.088314 0.119424 0.137112 0.241088 0 0 0 0.000571 0.5 160 11776 30500 0.419501 0.357991 0.0
25 25 0.392526 0.063745 0.418189 0.07255 384 29.490196 7.140242 12 49 54 8 0 1.057613 0.930267 0.443346 0.996192 0.0 -0.007609 1.148791 0.144086 0.038878 1.156401 0.084089 0.090011 0.143874 0.24259 0 0 0 0.000143 0.5 160 12288 31780 0.435626 0.36863 0.0
26 26 0.372018 0.059897 0.423848 0.071899 400 31.469388 7.203416 12 52 72 11 0 1.029235 0.934102 0.410439 0.996466 0.0 0.004522 1.162792 0.138072 0.037449 1.15827 0.08143 0.073596 0.132332 0.237737 0 0 0 0.0 0.5 160 12800 33060 0.452757 0.379858 0.0
27 27 0.370528 0.061527 0.416339 0.070829 416 32.711111 7.000617 11 53 81 9 0 0.994124 0.938992 0.37224 0.996779 0.0 -0.013493 1.177201 0.136202 0.036164 1.190694 0.078966 0.090944 0.136976 0.236829 0 0 0 0.0 0.5 160 13312 34340 0.47018 0.390013 0.0
28 28 0.369661 0.058027 0.420364 0.066734 432 31.603774 6.579729 11 53 73 12 0 0.965695 0.942944 0.341934 0.997008 0.0 0.007577 1.184773 0.138241 0.03519 1.177195 0.075412 0.078808 0.1104 0.241218 0 0 0 0.0 0.5 160 13824 35620 0.485198 0.400694 0.0
29 29 0.35543 0.058279 0.41508 0.061384 448 31.701923 6.698667 11 53 77 14 0 0.937896 0.946474 0.313856 0.997197 0.0 0.000451 1.193044 0.133464 0.034087 1.192593 0.072338 0.076651 0.104613 0.237811 0 0 0 0.0 0.5 160 14336 36900 0.501599 0.411847 0.0
30 30 0.337755 0.054846 0.413906 0.068532 464 34.944954 7.193739 12 55 95 14 0 0.910759 0.949997 0.286123 0.997387 0.0 -0.005675 1.204328 0.130593 0.033115 1.210003 0.070568 0.069911 0.130471 0.233913 0 0 0 0.0 0.5 160 14848 38180 0.519838 0.422685 0.0
31 31 0.336589 0.055247 0.405066 0.061001 480 33.320755 6.654191 13 55 80 16 0 0.885336 0.953173 0.260492 0.997548 0.0 -0.00443 1.212366 0.129309 0.032448 1.216796 0.068608 0.086287 0.10709 0.233276 0 0 0 0.0 0.5 160 15360 39460 0.53644 0.433521 0.0
32 32 0.331172 0.053983 0.395054 0.059603 496 35.611111 7.208435 12 58 102 6 0 0.85805 0.956508 0.2351 0.997687 0.0 -0.005361 1.220717 0.127784 0.031645 1.226077 0.065876 0.089135 0.097198 0.231731 0 0 0 0.0 0.5 160 15872 40740 0.553067 0.444488 0.0
33 33 0.322867 0.055785 0.385341 0.060871 512 36.423077 6.777559 13 58 101 3 0 0.831764 0.959519 0.211451 0.997806 0.0 0.004109 1.228642 0.126373 0.030805 1.224533 0.063179 0.078493 0.105754 0.230788 0 0 0 0.0 0.5 160 16384 42020 0.569614 0.455278 0.0
34 34 0.316523 0.052996 0.387693 0.06197 528 37.185185 7.605429 12 58 100 8 0 0.806511 0.962179 0.188612 0.997911 0.0 -0.002646 1.236243 0.130766 0.030106 1.238888 0.061536 0.064445 0.106228 0.234185 0 0 0 0.0 0.5 160 16896 43300 0.58623 0.466099 0.0
35 35 0.31197 0.054268 0.386364 0.060415 544 36.789474 7.408111 13 59 98 11 0 0.782158 0.964631 0.166797 0.998003 0.0 -0.002173 1.244094 0.130847 0.029335 1.246267 0.059446 0.082178 0.102195 0.23336 0 0 0 0.0 0.5 160 17408 44580 0.602651 0.476665 0.0
36 36 0.302595 0.052813 0.378512 0.056915 560 39.39823 7.647806 13 64 118 8 0 0.760821 0.966806 0.146943 0.998083 0.0 0.004135 1.249791 0.130553 0.028765 1.245656 0.056533 0.071456 0.094618 0.233314 0 0 0 0.0 0.5 160 17920 45860 0.619836 0.487301 0.0
37 37 0.294803 0.05077 0.371258 0.059246 576 39.453333 6.798623 14 61 121 4 0 0.737653 0.969026 0.126553 0.998165 0.0 -0.006499 1.257287 0.130013 0.0283 1.263786 0.05497 0.071902 0.104843 0.231632 0 0 0 0.0 0.5 160 18432 47140 0.63639 0.498077 0.0
38 38 0.292771 0.051039 0.369893 0.056795 592 40.295775 7.20739 14 64 130 12 0 0.71743 0.970975 0.109762 0.998233 0.0 -0.005988 1.261729 0.127363 0.027775 1.267718 0.053577 0.065417 0.10032 0.229631 0 0 0 0.0 0.5 160 18944 48420 0.652544 0.508912 0.0
39 39 0.288189 0.051083 0.36695 0.057009 608 40.390625 7.050465 14 65 133 9 0 0.696271 0.973016 0.092078 0.998303 0.0 -0.002612 1.267073 0.129422 0.027336 1.269685 0.052612 0.074157 0.100725 0.231659 0 0 0 0.0 0.5 160 19456 49700 0.669317 0.519411 0.0
40 40 0.282894 0.051902 0.35948 0.058951 624 39.719298 6.499275 14 61 113 10 0 0.677766 0.974806 0.076094 0.998364 0.0 -0.004201 1.271421 0.127537 0.026907 1.275622 0.05168 0.072164 0.10959 0.229801 0 0 0 0.0 0.5 160 19968 50980 0.685758 0.529969 0.0
41 41 0.277617 0.049926 0.359194 0.056578 640 41.008 7.244833 14 69 128 7 0 0.659624 0.976575 0.060607 0.998421 0.0 0.003034 1.275753 0.127812 0.026444 1.272718 0.050209 0.066631 0.102531 0.230189 0 0 0 0.0 0.5 160 20480 52260 0.702281 0.540695 0.0
42 42 0.27428 0.049464 0.352443 0.054773 656 40.770992 7.408704 14 71 123 8 0 0.641373 0.978335 0.045245 0.998478 0.0 -0.00206 1.27962 0.126502 0.026056 1.28168 0.048813 0.070713 0.1037 0.229173 0 0 0 0.0 0.5 160 20992 53540 0.719171 0.551391 0.0
43 43 0.270121 0.048912 0.348764 0.054183 672 42.123967 6.971788 14 69 146 7 0 0.624768 0.979969 0.031363 0.998528 0.0 -0.000502 1.283758 0.124538 0.025716 1.28426 0.047597 0.064818 0.10266 0.227358 0 0 0 0.0 0.5 160 21504 54820 0.735362 0.56188 0.0
44 44 0.26842 0.049693 0.351894 0.054645 688 42.230769 7.801455 14 69 148 8 0 0.607737 0.981607 0.017663 0.998577 0.0 0.009832 1.28698 0.128007 0.025374 1.277148 0.046476 0.06567 0.104433 0.230451 0 0 0 0.0 0.5 160 22016 56100 0.752069 0.572325 0.0
45 45 0.262164 0.048178 0.349015 0.054323 704 43.44 7.285355 14 68 154 4 0 0.591803 0.983127 0.005215 0.998621 0.0 0.00142 1.289226 0.124753 0.025046 1.287806 0.045624 0.063967 0.105745 0.227873 0 0 0 0.0 0.5 160 22528 57380 0.769501 0.582957 0.0
46 46 0.258718 0.047955 0.349694 0.052184 720 42.641509 7.091723 14 69 155 9 0 0.575638 0.984617 0.007584 0.998619 0.0 0.007958 1.292654 0.125694 0.02472 1.284696 0.044428 0.063016 0.098586 0.228911 0 0 0 0.0 0.5 160 23040 58660 0.785555 0.593544 0.0
47 47 0.255431 0.047305 0.344331 0.050948 736 44.228916 7.572393 14 69 172 9 0 0.561413 0.98597 0.014748 0.998579 0.0 0.003276 1.294295 0.125635 0.024515 1.291019 0.04355 0.067624 0.101547 0.228781 0 0 0 0.0 0.5 160 23552 59940 0.801486 0.60424 0.0
48 48 0.250001 0.047848 0.341333 0.051525 752 44.111111 7.264006 14 73 161 11 0 0.546717 0.987367 0.026728 0.998536 0.0 -0.005279 1.297264 0.126192 0.024296 1.302543 0.042292 0.064979 0.101446 0.229475 0 0 0 0.0 0.5 160 24064 61220 0.818276 0.614825 0.0
49 49 0.245609 0.047684 0.341277 0.050984 768 45.26087 7.373926 14 72 176 4 0 0.532707 0.988651 0.039098 0.998493 0.0 0.005743 1.299071 0.126101 0.024111 1.293329 0.04193 0.056811 0.100948 0.229463 0 0 0 0.0 0.5 160 24576 62500 0.834776 0.625418 0.0
50 50 0.242437 0.046703 0.341888 0.051188 784 45.401639 7.75712 14 76 181 2 0 0.518698 0.989949 0.051377 0.998451 0.0 -0.001614 1.301167 0.128256 0.023945 1.302781 0.040973 0.056158 0.102376 0.231603 0 0 0 0.0 0.5 160 25088 63780 0.851443 0.63612 0.0
51 51 0.238025 0.046858 0.339849 0.050796 800 46.322581 7.785749 14 76 191 3 0 0.506391 0.991102 0.063148 0.998409 0.0 -0.001425 1.302592 0.126662 0.023774 1.304017 0.040351 0.055895 0.101336 0.229748 0 0 0 0.0 0.5 160 25600 65060 0.867788 0.646752 0.0
52 52 0.235722 0.046926 0.337508 0.050981 816 47.336449 7.75545 14 77 201 3 0 0.493941 0.992259 0.074642 0.998367 0.0 0.004116 1.30427 0.126909 0.023644 1.300154 0.039552 0.052704 0.102293 0.229956 0 0 0 0.0 0.5 160 26112 66340 0.88439 0.657337 0.0
53 53 0.232174 0.046489 0.334001 0.050079 832 48.548387 7.560846 14 79 210 1 0 0.48219 0.993345 0.085285 0.998327 0.0 -0.003808 1.306103 0.125471 0.023548 1.309911 0.038814 0.05415 0.099596 0.228384 0 0 0 0.0 0.5 160 26624 67620 0.900553 0.667999 0.0
54 54 0.229425 0.046268 0.333985 0.051411 848 48.94697 8.011701 14 79 216 3 0 0.469948 0.994473 0.095813 0.998288 0.0 0.00261 1.307902 0.126487 0.023453 1.305292 0.038029 0.049963 0.104023 0.229507 0 0 0 0.0 0.5 160 27136 68900 0.917167 0.678567 0.0
55 55 0.225629 0.045671 0.333841 0.050444 864 49.621622 7.733504 14 80 221 1 0 0.458472 0.995515 0.105779 0.998251 0.0 -0.005091 1.309114 0.125269 0.023362 1.314205 0.037295 0.054362 0.101336 0.228565 0 0 0 0.0 0.5 160 27648 70180 0.933438 0.689082 0.0
56 56 0.2222 0.045819 0.33204 0.050985 880 50.42268 7.953624 14 80 232 0 0 0.447146 0.996531 0.115254 0.998214 0.0 -0.001742 1.310496 0.126043 0.023274 1.312238 0.036776 0.053944 0.10229 0.229248 0 0 0 0.0 0.5 160 28160 71460 0.949952 0.699724 0.0
57 57 0.21936 0.045682 0.329337 0.050342 896 50.275362 7.532466 14 81 230 1 0 0.435607 0.997552 0.124412 0.998177 0.0 -0.001953 1.312043 0.122593 0.023218 1.313996 0.036236 0.053687 0.101384 0.226985 0 0 0 0.0 0.5 160 28672 72740 0.96667 0.710367 0.0
58 58 0.217617 0.045773 0.329427 0.050387 912 51.179104 7.570606 14 83 241 0 0 0.425287 0.998462 0.132604 0.998143 0.0 0.005332 1.313334 0.12586 0.023143 1.308002 0.035845 0.051438 0.101005 0.230025 0 0 0 0.0 0.5 160 29184 74020 0.982691 0.720876 0.0
59 59 0.214483 0.045108 0.32928 0.050517 928 52.417266 7.459617 14 83 253 0 0 0.41487 0.999405 0.140359 0.99811 0.0 -0.007991 1.315325 0.123002 0.023103 1.323316 0.035248 0.052316 0.101684 0.227699 0 0 0 0.0 0.5 160 29696 75300 0.999041 0.731442 0.0
60 60 0.212822 0.045598 0.328814 0.050153 944 53.065217 7.638715 14 84 262 0 0 0.404307 1.00036 0.1477 0.998077 0.0 -0.001584 1.316404 0.124876 0.023036 1.317988 0.034869 0.047921 0.102206 0.229367 0 0 0 0.0 0.5 160 30208 76580 1.015249 0.741992 0.0
61 61 0.209714 0.04528 0.326136 0.04986 960 53.321678 7.905541 14 84 266 0 0 0.394078 1.001277 0.154419 0.998046 0.0 0.002836 1.317499 0.12624 0.023011 1.314663 0.034654 0.048552 0.10215 0.230449 0 0 0 0.0 0.5 160 30720 77860 1.032277 0.752596 0.0
62 62 0.207956 0.045773 0.326124 0.049355 976 54.250909 7.925115 14 86 279 0 0 0.384951 1.002144 0.160454 0.998017 0.0 -0.004175 1.318179 0.125767 0.022954 1.322354 0.034075 0.04808 0.101525 0.230158 0 0 0 0.0 0.5 160 31232 79140 1.048592 0.76319 0.0
63 63 0.205865 0.045522 0.325502 0.049669 992 54.972727 8.054637 14 87 285 0 0 0.374974 1.003039 0.166267 0.997988 0.0 -0.007319 1.319265 0.12619 0.022906 1.326584 0.033753 0.048784 0.102105 0.230666 0 0 0 0.0 0.5 160 31744 80420 1.064614 0.773764 0.0
64 64 0.20481 0.04572 0.323759 0.04921 1008 56.114286 8.142942 14 89 299 0 0 0.366281 1.003879 0.17142 0.997962 0.0 0.000893 1.320418 0.125666 0.022866 1.319525 0.033461 0.045723 0.101934 0.230405 0 0 0 0.0 0.5 160 32256 81700 1.081145 0.784281 0.0
65 65 0.202293 0.044739 0.323196 0.049169 1024 56.864407 7.775636 14 91 309 0 0 0.356818 1.004805 0.176803 0.997934 0.0 -0.002565 1.321171 0.124942 0.022818 1.323736 0.032762 0.043384 0.102697 0.229858 0 0 0 0.0 0.5 160 32768 82980 1.097665 0.794777 0.0
66 66 0.200657 0.044541 0.321191 0.049166 1040 57.632 7.686043 14 92 318 0 0 0.348494 1.005622 0.181448 0.997909 0.0 0.005914 1.322568 0.124562 0.02278 1.316654 0.032371 0.043402 0.103388 0.229591 0 0 0 0.0 0.5 160 33280 84260 1.114221 0.805217 0.0
67 67 0.199381 0.044401 0.320988 0.04917 1056 58.17284 7.520472 14 93 326 0 0 0.340254 1.006442 0.18598 0.997884 0.0 0.007393 1.323599 0.123656 0.022738 1.316206 0.031999 0.040186 0.103543 0.228777 0 0 0 0.0 0.5 160 33792 85540 1.13041 0.815693 0.0
68 68 0.197356 0.044644 0.319935 0.049349 1072 58.452991 7.548847 14 94 332 0 0 0.332015 1.007239 0.190375 0.997858 0.0 -0.006819 1.324413 0.125372 0.022699 1.331232 0.031497 0.040772 0.104793 0.230536 0 0 0 0.0 0.5 160 34304 86820 1.146482 0.826154 0.0
69 69 0.195273 0.043788 0.319338 0.049681 1088 58.915663 7.267614 14 94 338 0 0 0.323803 1.008052 0.194749 0.997834 0.0 -0.001197 1.325726 0.123478 0.022679 1.326923 0.031077 0.04086 0.105203 0.229429 0 0 0 0.0 0.5 160 34816 88100 1.162608 0.836667 0.0
70 70 0.194437 0.044469 0.318931 0.049299 1104 59.639535 7.286842 14 96 348 0 0 0.316215 1.008814 0.198645 0.99781 0.0 -0.001692 1.32667 0.124628 0.022624 1.328363 0.030721 0.039682 0.10517 0.23039 0 0 0 0.0 0.5 160 35328 89380 1.178974 0.847163 0.0
71 71 0.192687 0.043957 0.31859 0.049431 1120 60.188506 7.157111 14 97 356 0 0 0.30853 1.009578 0.202448 0.997787 0.0 0.000977 1.327879 0.124042 0.022593 1.326902 0.030444 0.040629 0.105291 0.230007 0 0 0 0.0 0.5 160 35840 90660 1.194753 0.857645 0.0
72 72 0.191614 0.043857 0.31774 0.049668 1136 60.722222 7.031552 14 98 365 0 0 0.300858 1.010324 0.206198 0.997764 0.0 0.00287 1.328997 0.123559 0.022561 1.326127 0.030126 0.039866 0.105438 0.229652 0 0 0 0.0 0.5 160 36352 91940 1.21084 0.868093 0.0
73 73 0.190116 0.043972 0.316243 0.049351 1152 61.222222 6.950291 14 99 373 0 0 0.293111 1.011091 0.209948 0.997741 0.0 -0.001143 1.329416 0.123199 0.022542 1.330558 0.029802 0.037706 0.105458 0.229359 0 0 0 0.0 0.5 160 36864 93220 1.226781 0.878531 0.0
74 74 0.188823 0.043603 0.31586 0.04979 1168 61.764706 6.71819 14 99 382 0 0 0.285899 1.011805 0.213539 0.99772 0.0 0.001683 1.330196 0.12138 0.022518 1.328513 0.029513 0.038635 0.106055 0.228252 0 0 0 0.0 0.5 160 37376 94500 1.243166 0.888947 0.0
75 75 0.187946 0.04395 0.315312 0.049826 1184 62.502762 6.52862 14 101 393 0 0 0.278758 1.012508 0.217043 0.997699 0.0 -0.001978 1.330932 0.123709 0.022486 1.33291 0.029223 0.037615 0.106101 0.230143 0 0 0 0.0 0.5 160 37888 95780 1.259163 0.899367 0.0
76 76 0.18693 0.043793 0.315309 0.049577 1200 63.01081 6.591101 14 101 400 0 0 0.271584 1.013233 0.220528 0.997678 0.0 -0.005166 1.331491 0.122407 0.022468 1.336657 0.028999 0.038693 0.106267 0.229157 0 0 0 0.0 0.5 160 38400 97060 1.275559 0.909783 0.0
77 77 0.185725 0.043772 0.314445 0.049665 1216 63.5 6.533883 14 102 407 0 0 0.264459 1.013944 0.223961 0.997657 0.0 -0.000345 1.33238 0.122581 0.022443 1.332725 0.028661 0.037001 0.106125 0.229389 0 0 0 0.0 0.5 160 38912 98340 1.291633 0.920197 0.0
78 78 0.184374 0.043845 0.313223 0.049474 1232 63.868421 6.332364 14 102 412 0 0 0.257369 1.014651 0.227347 0.997637 0.0 -0.001788 1.332894 0.123657 0.022421 1.334682 0.02852 0.037331 0.106447 0.230166 0 0 0 0.0 0.5 160 39424 99620 1.307461 0.930658 0.0
79 79 0.183369 0.043799 0.313189 0.049945 1248 64.031579 6.22299 14 103 416 0 0 0.250621 1.015329 0.230579 0.997617 0.0 -0.004994 1.333109 0.12253 0.022408 1.338104 0.028115 0.036283 0.107077 0.229651 0 0 0 0.0 0.5 160 39936 100900 1.323431 0.941093 0.0
80 80 0.182313 0.043803 0.313621 0.049504 1264 64.772021 6.283663 14 104 426 0 0 0.244079 1.015983 0.23382 0.997598 0.0 -0.000674 1.333639 0.122729 0.022391 1.334313 0.027864 0.036994 0.10729 0.229839 0 0 0 0.0 0.5 160 40448 102180 1.339805 0.951507 0.0
81 81 0.18118 0.043537 0.31299 0.04942 1280 65.145833 6.135349 14 105 432 0 0 0.237416 1.016668 0.237026 0.997578 0.0 -0.001204 1.334106 0.121346 0.022379 1.33531 0.027636 0.036351 0.107356 0.228703 0 0 0 0.0 0.5 160 40960 103460 1.355741 0.961968 0.0
82 82 0.180577 0.043543 0.31268 0.049472 1296 65.410256 6.037151 14 105 436 0 0 0.231037 1.017337 0.240113 0.997559 0.0 0.002887 1.33445 0.121665 0.022368 1.331562 0.027416 0.036869 0.107655 0.22932 0 0 0 0.0 0.5 160 41472 104740 1.371833 0.972396 0.0
83 83 0.179241 0.043605 0.312299 0.049383 1312 65.931707 5.995037 14 107 444 0 0 0.224641 1.017994 0.243163 0.99754 0.0 -0.001478 1.335015 0.122094 0.022355 1.336493 0.027021 0.036385 0.107739 0.22977 0 0 0 0.0 0.5 160 41984 106020 1.38804 0.982833 0.0
84 84 0.178763 0.043397 0.311798 0.049272 1328 66.58 5.973742 14 108 453 0 0 0.218375 1.018638 0.246128 0.997522 0.0 -0.00086 1.335699 0.121005 0.022342 1.336559 0.026698 0.035307 0.107661 0.228666 0 0 0 0.0 0.5 160 42496 107300 1.404244 0.993277 0.0
85 85 0.17784 0.0435 0.311295 0.049092 1344 67.123077 5.853671 14 108 460 0 0 0.212339 1.019262 0.24895 0.997503 0.0 0.001913 1.336019 0.121107 0.022332 1.334106 0.026373 0.03447 0.107791 0.228883 0 0 0 0.0 0.5 160 43008 108580 1.420617 1.003708 0.0
86 86 0.177057 0.043582 0.31126 0.04922 1360 67.454545 5.922791 14 109 465 0 0 0.206311 1.019883 0.251825 0.997485 0.0 -0.00415 1.336489 0.120894 0.022325 1.340639 0.026152 0.034548 0.108365 0.228966 0 0 0 0.0 0.5 160 43520 109860 1.437031 1.014155 0.0
87 87 0.176068 0.043563 0.311033 0.049082 1376 67.511279 5.76857 14 109 466 0 0 0.200313 1.02051 0.254637 0.997468 0.0 0.000396 1.337082 0.120344 0.022314 1.336686 0.02582 0.034124 0.108481 0.228452 0 0 0 0.0 0.5 160 44032 111140 1.453405 1.024602 0.0
88 88 0.175247 0.043504 0.310325 0.049199 1392 67.966292 5.87116 14 111 473 0 0 0.194704 1.021095 0.257318 0.997451 0.0 -0.000842 1.337572 0.120782 0.022307 1.338413 0.025523 0.033778 0.108785 0.229567 0 0 0 0.0 0.5 160 44544 112420 1.469359 1.035023 0.0
89 89 0.174255 0.043402 0.309799 0.049186 1408 68.446154 5.657494 14 111 479 0 0 0.188885 1.021721 0.259913 0.997435 0.0 -0.000371 1.33787 0.120144 0.022303 1.338241 0.025156 0.033415 0.108929 0.228667 0 0 0 0.0 0.5 160 45056 113700 1.485497 1.045451 0.0
90 90 0.173753 0.043502 0.309344 0.049098 1424 68.689655 5.568486 14 111 483 0 0 0.183197 1.022315 0.26254 0.997419 0.0 -0.000882 1.33817 0.120151 0.022297 1.339052 0.024962 0.033364 0.109001 0.228486 0 0 0 0.0 0.5 160 45568 114980 1.501641 1.055862 0.0
91 91 0.172915 0.043444 0.309403 0.049264 1440 69.375 5.364643 14 113 491 0 0 0.177724 1.022877 0.26508 0.997404 0.0 -0.001672 1.338883 0.119721 0.022293 1.340555 0.024721 0.033772 0.109458 0.22872 0 0 0 0.0 0.5 160 46080 116260 1.517742 1.066291 0.0
92 92 0.172222 0.043363 0.309174 0.04913 1456 69.702128 5.232866 14 114 496 0 0 0.172468 1.023432 0.267487 0.997389 0.0 -0.001972 1.339316 0.119488 0.022285 1.341288 0.024468 0.0339 0.109704 0.228541 0 0 0 0.0 0.5 160 46592 117540 1.533956 1.076715 0.0
93 93 0.171628 0.043518 0.309136 0.048953 1472 69.510638 5.379782 14 113 493 0 0 0.166978 1.023994 0.269858 0.997374 0.0 0.001447 1.339841 0.120601 0.022279 1.338394 0.024241 0.033853 0.110019 0.229193 0 0 0 0.0 0.5 160 47104 118820 1.550249 1.087117 0.0
94 94 0.171101 0.043435 0.308574 0.048836 1488 70.583333 5.261782 14 114 507 0 0 0.161537 1.024538 0.272173 0.997359 0.0 -0.000902 1.340268 0.119553 0.022273 1.34117 0.023988 0.032935 0.110091 0.228271 0 0 0 0.0 0.5 160 47616 120100 1.566651 1.097526 0.0
95 95 0.170627 0.043532 0.308325 0.049205 1504 71.270833 5.158098 14 116 515 0 0 0.156447 1.025074 0.274438 0.997345 0.0 0.000379 1.340701 0.119783 0.022267 1.340322 0.023774 0.032319 0.110161 0.228587 0 0 0 0.0 0.5 160 48128 121380 1.582545 1.107941 0.0
96 96 0.169751 0.043403 0.308115 0.049029 1520 71.893617 5.170339 14 116 522 0 0 0.151571 1.025587 0.27652 0.997332 0.0 -0.001231 1.341004 0.119741 0.022262 1.342235 0.023526 0.032626 0.110304 0.228611 0 0 0 0.0 0.5 160 48640 122660 1.59872 1.11834 0.0
97 97 0.169234 0.043432 0.307972 0.048982 1536 72.020833 4.959266 14 117 524 0 0 0.146562 1.026129 0.278726 0.997318 0.0 0.000839 1.341299 0.118758 0.022258 1.34046 0.023301 0.032262 0.110456 0.22779 0 0 0 0.0 0.5 160 49152 123940 1.614703 1.128732 0.0
98 98 0.16869 0.043446 0.307625 0.049033 1552 72.622449 4.900331 14 117 531 0 0 0.141862 1.026643 0.280802 0.997305 0.0 -0.001613 1.341635 0.118799 0.022255 1.343249 0.023054 0.031614 0.110748 0.228282 0 0 0 0.0 0.5 160 49664 125220 1.630856 1.139141 0.0
99 99 0.16811 0.043428 0.307104 0.048985 1568 73.237113 4.765278 14 119 538 0 0 0.137326 1.02715 0.282838 0.997292 0.0 -0.000388 1.341861 0.118292 0.022251 1.342249 0.022834 0.031508 0.111022 0.227997 0 0 0 0.0 0.5 160 50176 126500 1.647085 1.149526 0.0
100 100 0.167596 0.04339 0.306859 0.049024 1584 73.90404 4.707967 14 119 545 0 0 0.132781 1.027633 0.284799 0.99728 0.0 -0.000576 1.342066 0.117859 0.022247 1.342642 0.022583 0.031278 0.111163 0.22775 0 0 0 0.0 0.5 160 50688 127780 1.66343 1.159925 0.0

AlphaZero-Style MCTS Training Metrics (212 Iterations) — Analysis

Policy loss dropped 94% (2.33 → 0.14) over 212 iterations — the agent learned a strong policy from scratch

By iteration 45 the agent stopped losing entirely, winning 100% of self-play games for the remaining 167 iterations

Training Summary

  • Policy loss fell from 2.33 to 0.14 (94% drop), with most improvement in the first 50 iterations
  • Value loss collapsed from 0.61 to 0.04 (93% drop), meaning the network learned to predict game outcomes accurately
  • Average game length tripled from 35 to 110 moves as the agent learned to exploit the full game tree
  • Early-game value error improved from 0.35 to 0.02, but late-game error worsened from 0.46 to 0.12 — the agent calibrates openings well but struggles with endgame evaluation
  • Validation policy loss (0.30) is 2x the training loss (0.14), indicating moderate overfitting to the replay buffer

Visualizations

Value Prediction Errors
Self-Play Win Rate
Average Game Length
Policy Loss: Train vs Validation

Embed this dataset

Paste this code into your blog or website. Readers can search, sort, and paginate the data.

<iframe src="https://data.tablepage.ai/d/alphazero-style-mcts-training-metrics-212-iterations?embed=1" width="100%" height="500" frameborder="0"></iframe>

Works on WordPress, Ghost, and any site that supports iframes.

Related Datasets

AlphaZero-Style MCTS Training Metrics (103 Iterations)

Policy loss, value error, game length, and MCTS agreement metrics across 103 self-play training iterations.

103 rows · 49 cols

AlphaZero Training Run: 62-Iteration Self-Play Metrics

Policy loss, value loss, game length, and MCTS agreement metrics across 62 iterations of AlphaZero-style reinforcement l...

62 rows · 51 cols

AlphaZero-Style RL Training Metrics (13 Iterations)

Policy and value network training logs tracking losses, game length, MCTS agreement, and value calibration across 13 sel...

13 rows · 51 cols