Add 2-player PPO training log (500k episodes, 60.4% vs greedy)HEADmain

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

1 files changed, 201 insertions, 0 deletions

diff --git a/blazing_ppo_2p_log.csv b/blazing_ppo_2p_log.csv
new file mode 100644
index 0000000..98d8508
--- /dev/null
+++ b/blazing_ppo_2p_log.csv
@@ -0,0 +1,201 @@
+episode,avg_len,loss,vs_greedy_wr
+2560,57.9,0.0361,0.4310
+5120,73.0,0.0000,0.4225
+7680,86.2,-0.0074,0.4450
+10240,78.6,0.0000,0.4710
+12800,78.3,-0.0095,0.4805
+15360,87.3,0.0000,0.4790
+17920,86.6,-0.0158,0.4430
+20480,94.6,0.0000,0.4730
+22528,87.2,-0.0105,0.4640
+25088,83.6,0.0000,0.4600
+27648,88.7,-0.0233,0.4825
+30208,92.6,0.0000,0.4905
+32768,92.2,-0.0196,0.5035
+35328,80.3,0.0000,0.4955
+37888,78.0,-0.0084,0.4890
+40448,91.9,0.0000,0.4785
+43008,94.2,0.0000,0.4900
+45056,88.5,0.0000,0.5105
+47616,84.7,-0.0076,0.5205
+50176,82.3,0.0000,0.4925
+52736,82.2,-0.0025,0.4880
+55296,88.9,0.0000,0.4910
+57856,81.0,0.0022,0.5080
+60416,79.4,0.0000,0.5080
+62976,81.4,0.0004,0.5215
+65024,81.2,0.0000,0.5030
+67584,71.8,0.0157,0.5365
+70144,69.9,0.0000,0.5255
+72704,73.3,0.0089,0.4995
+75264,74.3,0.0000,0.5510
+77824,72.4,0.0132,0.5160
+80384,72.6,0.0000,0.5305
+82944,73.1,0.0048,0.5310
+85504,78.4,0.0000,0.5140
+87552,82.7,0.0012,0.4965
+90112,79.8,0.0000,0.5240
+92672,77.8,0.0167,0.5065
+95232,72.2,0.0000,0.5235
+97792,74.3,0.0153,0.5255
+100352,73.7,0.0000,0.5240
+102912,72.8,0.0185,0.5255
+105472,79.8,0.0000,0.5095
+107520,80.6,0.0114,0.5205
+110080,81.1,0.0000,0.5150
+112640,79.4,0.0114,0.5210
+115200,77.4,0.0000,0.5260
+117760,76.8,0.0166,0.5035
+120320,78.9,0.0000,0.5110
+122880,76.0,0.0175,0.5320
+125440,70.4,0.0000,0.5350
+128000,71.3,0.0000,0.5405
+130048,70.8,0.0000,0.5350
+132608,68.1,0.0305,0.5465
+135168,66.7,0.0000,0.5445
+137728,72.2,0.0138,0.5240
+140288,72.2,0.0000,0.5385
+142848,68.9,0.0257,0.5570
+145408,63.7,0.0000,0.5575
+147968,64.7,0.0315,0.5415
+150016,67.4,0.0000,0.5540
+152576,65.1,0.0356,0.5365
+155136,67.3,0.0000,0.5415
+157696,67.1,0.0333,0.5475
+160256,65.8,0.0000,0.5550
+162816,65.2,0.0412,0.5530
+165376,62.4,0.0000,0.5495
+167936,60.4,0.0413,0.5500
+170496,60.9,0.0000,0.5535
+172544,59.8,0.0437,0.5590
+175104,65.4,0.0000,0.5575
+177664,63.4,0.0413,0.5615
+180224,64.2,0.0000,0.5590
+182784,64.5,0.0346,0.5520
+185344,65.6,0.0000,0.5415
+187904,62.7,0.0443,0.5470
+190464,63.2,0.0000,0.5545
+192512,64.3,0.0407,0.5470
+195072,68.1,0.0000,0.5275
+197632,71.4,0.0234,0.5425
+200192,71.1,0.0000,0.5415
+202752,66.9,0.0362,0.5540
+205312,68.2,0.0000,0.5630
+207872,65.5,0.0378,0.5395
+210432,68.4,0.0000,0.5575
+212992,66.0,0.0335,0.5675
+215040,68.6,0.0000,0.5385
+217600,66.6,0.0339,0.5695
+220160,65.8,0.0000,0.5790
+222720,64.1,0.0339,0.5825
+225280,65.0,0.0000,0.5425
+227840,67.0,0.0388,0.5695
+230400,64.4,0.0000,0.5905
+232960,65.5,0.0380,0.5440
+235008,63.3,0.0000,0.5500
+237568,61.3,0.0503,0.5745
+240128,59.6,0.0000,0.5795
+242688,59.7,0.0475,0.5345
+245248,62.6,0.0000,0.5790
+247808,61.2,0.0470,0.5525
+250368,66.0,0.0000,0.5650
+252928,62.2,0.0516,0.5565
+255488,61.1,0.0000,0.5970
+257536,60.4,0.0517,0.5755
+260096,63.9,0.0000,0.5750
+262656,65.2,0.0483,0.5740
+265216,65.9,0.0000,0.5845
+267776,62.4,0.0510,0.5635
+270336,67.2,0.0000,0.5525
+272896,65.2,0.0335,0.5510
+275456,64.7,0.0000,0.5765
+277504,63.3,0.0000,0.5555
+280064,62.5,0.0000,0.5745
+282624,62.2,0.0505,0.5700
+285184,61.8,0.0000,0.5770
+287744,59.8,0.0537,0.5860
+290304,57.0,0.0000,0.5640
+292864,57.7,0.0663,0.5820
+295424,58.0,0.0000,0.5760
+297984,59.1,0.0585,0.5715
+300032,58.1,0.0000,0.5835
+302592,59.8,0.0548,0.5815
+305152,60.5,0.0000,0.5985
+307712,60.9,0.0534,0.5840
+310272,62.2,0.0000,0.5700
+312832,63.3,0.0527,0.5780
+315392,62.2,0.0000,0.5685
+317952,59.1,0.0535,0.6080
+320000,60.1,0.0000,0.5875
+322560,62.6,0.0525,0.5585
+325120,58.1,0.0000,0.5870
+327680,60.6,0.0496,0.5865
+330240,61.2,0.0000,0.5890
+332800,60.0,0.0560,0.5725
+335360,60.8,0.0000,0.5860
+337920,59.8,0.0597,0.5915
+340480,59.7,0.0000,0.5715
+342528,61.2,0.0577,0.5785
+345088,60.2,0.0000,0.5830
+347648,59.8,0.0589,0.5920
+350208,58.9,0.0000,0.5965
+352768,58.2,0.0639,0.5800
+355328,58.7,0.0000,0.6015
+357888,59.4,0.0633,0.5805
+360448,57.3,0.0000,0.5755
+363008,58.9,0.0000,0.5840
+365056,59.6,0.0000,0.5760
+367616,59.9,0.0624,0.5735
+370176,57.9,0.0000,0.5675
+372736,58.8,0.0681,0.5780
+375296,59.0,0.0000,0.5960
+377856,57.8,0.0665,0.5895
+380416,56.8,0.0000,0.5995
+382976,57.3,0.0658,0.6000
+385024,60.6,0.0000,0.5955
+387584,57.5,0.0666,0.5980
+390144,56.5,0.0000,0.5935
+392704,57.2,0.0695,0.5730
+395264,55.6,0.0000,0.5870
+397824,59.0,0.0629,0.5880
+400384,57.3,0.0000,0.6110
+402944,56.5,0.0644,0.5985
+405504,58.3,0.0000,0.5980
+407552,58.1,0.0586,0.5985
+410112,58.6,0.0000,0.6030
+412672,59.0,0.0680,0.6050
+415232,57.4,0.0000,0.5940
+417792,57.9,0.0715,0.5780
+420352,56.8,0.0000,0.5910
+422912,55.8,0.0756,0.5915
+425472,57.1,0.0000,0.6035
+427520,58.0,0.0696,0.5960
+430080,57.4,0.0000,0.5925
+432640,59.2,0.0694,0.6030
+435200,59.5,0.0000,0.6175
+437760,56.1,0.0755,0.6110
+440320,59.2,0.0000,0.5825
+442880,61.5,0.0657,0.6010
+445440,61.0,0.0000,0.5875
+448000,62.9,0.0000,0.6000
+450048,60.0,0.0000,0.6030
+452608,57.8,0.0720,0.6160
+455168,55.8,0.0000,0.5905
+457728,55.2,0.0781,0.6050
+460288,57.9,0.0000,0.5970
+462848,56.5,0.0768,0.6050
+465408,58.7,0.0000,0.6055
+467968,60.1,0.0680,0.6360
+470016,61.0,0.0000,0.6115
+472576,60.0,0.0797,0.6050
+475136,60.8,0.0000,0.6005
+477696,61.6,0.0770,0.6000
+480256,60.6,0.0000,0.6110
+482816,62.5,0.0720,0.5970
+485376,61.1,0.0000,0.6150
+487936,60.4,0.0744,0.6110
+490496,60.8,0.0000,0.6125
+492544,59.3,0.0755,0.6155
+495104,58.6,0.0000,0.6330
+497664,55.1,0.0825,0.6200
+500000,56.3,0.0000,0.6120