HardikJha commited on
Commit
ccc9e32
·
verified ·
1 Parent(s): c24bb35

Add eval metrics (100 eps)

Browse files
Files changed (1) hide show
  1. eval_metrics.json +802 -0
eval_metrics.json ADDED
@@ -0,0 +1,802 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ [
2
+ {
3
+ "episode": 0,
4
+ "extractor_reward": 0.0,
5
+ "adversary_reward": 0.5,
6
+ "extractor_elo": 1184.0,
7
+ "adversary_elo": 1216.0,
8
+ "edits_applied": 0
9
+ },
10
+ {
11
+ "episode": 1,
12
+ "extractor_reward": 0.0,
13
+ "adversary_reward": 0.0,
14
+ "extractor_elo": 1169.4695015289756,
15
+ "adversary_elo": 1230.5304984710244,
16
+ "edits_applied": 0
17
+ },
18
+ {
19
+ "episode": 2,
20
+ "extractor_reward": 0.0,
21
+ "adversary_reward": 0.0,
22
+ "extractor_elo": 1156.252866366389,
23
+ "adversary_elo": 1243.747133633611,
24
+ "edits_applied": 0
25
+ },
26
+ {
27
+ "episode": 3,
28
+ "extractor_reward": 0.0,
29
+ "adversary_reward": 0.0,
30
+ "extractor_elo": 1144.1990573710023,
31
+ "adversary_elo": 1255.8009426289977,
32
+ "edits_applied": 0
33
+ },
34
+ {
35
+ "episode": 4,
36
+ "extractor_reward": 0.0,
37
+ "adversary_reward": 0.0,
38
+ "extractor_elo": 1133.1687543796,
39
+ "adversary_elo": 1266.8312456204,
40
+ "edits_applied": 0
41
+ },
42
+ {
43
+ "episode": 5,
44
+ "extractor_reward": 0.0,
45
+ "adversary_reward": 0.0,
46
+ "extractor_elo": 1123.0374294577985,
47
+ "adversary_elo": 1276.9625705422015,
48
+ "edits_applied": 1
49
+ },
50
+ {
51
+ "episode": 6,
52
+ "extractor_reward": 0.0,
53
+ "adversary_reward": 0.0,
54
+ "extractor_elo": 1113.6959037914467,
55
+ "adversary_elo": 1286.3040962085533,
56
+ "edits_applied": 1
57
+ },
58
+ {
59
+ "episode": 7,
60
+ "extractor_reward": 0.0,
61
+ "adversary_reward": 0.0,
62
+ "extractor_elo": 1105.049532366863,
63
+ "adversary_elo": 1294.950467633137,
64
+ "edits_applied": 0
65
+ },
66
+ {
67
+ "episode": 8,
68
+ "extractor_reward": 0.0,
69
+ "adversary_reward": 0.0,
70
+ "extractor_elo": 1097.016759966111,
71
+ "adversary_elo": 1302.983240033889,
72
+ "edits_applied": 0
73
+ },
74
+ {
75
+ "episode": 9,
76
+ "extractor_reward": 0.0,
77
+ "adversary_reward": 0.0,
78
+ "extractor_elo": 1089.527482596379,
79
+ "adversary_elo": 1310.472517403621,
80
+ "edits_applied": 0
81
+ },
82
+ {
83
+ "episode": 10,
84
+ "extractor_reward": 0.0,
85
+ "adversary_reward": 0.0,
86
+ "extractor_elo": 1082.5214442230742,
87
+ "adversary_elo": 1317.4785557769258,
88
+ "edits_applied": 0
89
+ },
90
+ {
91
+ "episode": 11,
92
+ "extractor_reward": 0.0,
93
+ "adversary_reward": 0.0,
94
+ "extractor_elo": 1075.946775904531,
95
+ "adversary_elo": 1324.053224095469,
96
+ "edits_applied": 0
97
+ },
98
+ {
99
+ "episode": 12,
100
+ "extractor_reward": 0.0,
101
+ "adversary_reward": 0.0,
102
+ "extractor_elo": 1069.7587157846353,
103
+ "adversary_elo": 1330.2412842153647,
104
+ "edits_applied": 1
105
+ },
106
+ {
107
+ "episode": 13,
108
+ "extractor_reward": 0.0,
109
+ "adversary_reward": 0.0,
110
+ "extractor_elo": 1063.918512725068,
111
+ "adversary_elo": 1336.081487274932,
112
+ "edits_applied": 0
113
+ },
114
+ {
115
+ "episode": 14,
116
+ "extractor_reward": 0.0,
117
+ "adversary_reward": 0.0,
118
+ "extractor_elo": 1058.392499592162,
119
+ "adversary_elo": 1341.607500407838,
120
+ "edits_applied": 0
121
+ },
122
+ {
123
+ "episode": 15,
124
+ "extractor_reward": 0.0,
125
+ "adversary_reward": 0.0,
126
+ "extractor_elo": 1053.1513157470686,
127
+ "adversary_elo": 1346.8486842529314,
128
+ "edits_applied": 0
129
+ },
130
+ {
131
+ "episode": 16,
132
+ "extractor_reward": 0.0,
133
+ "adversary_reward": 0.0,
134
+ "extractor_elo": 1048.169257121525,
135
+ "adversary_elo": 1351.830742878475,
136
+ "edits_applied": 1
137
+ },
138
+ {
139
+ "episode": 17,
140
+ "extractor_reward": 0.0,
141
+ "adversary_reward": 0.0,
142
+ "extractor_elo": 1043.4237336047115,
143
+ "adversary_elo": 1356.5762663952885,
144
+ "edits_applied": 0
145
+ },
146
+ {
147
+ "episode": 18,
148
+ "extractor_reward": 0.0,
149
+ "adversary_reward": 0.0,
150
+ "extractor_elo": 1038.8948158212902,
151
+ "adversary_elo": 1361.1051841787098,
152
+ "edits_applied": 1
153
+ },
154
+ {
155
+ "episode": 19,
156
+ "extractor_reward": 0.0,
157
+ "adversary_reward": 0.0,
158
+ "extractor_elo": 1034.5648559791382,
159
+ "adversary_elo": 1365.4351440208618,
160
+ "edits_applied": 1
161
+ },
162
+ {
163
+ "episode": 20,
164
+ "extractor_reward": 0.0,
165
+ "adversary_reward": 0.0,
166
+ "extractor_elo": 1030.4181699412484,
167
+ "adversary_elo": 1369.5818300587516,
168
+ "edits_applied": 1
169
+ },
170
+ {
171
+ "episode": 21,
172
+ "extractor_reward": 0.0,
173
+ "adversary_reward": 0.0,
174
+ "extractor_elo": 1026.440769877527,
175
+ "adversary_elo": 1373.559230122473,
176
+ "edits_applied": 0
177
+ },
178
+ {
179
+ "episode": 22,
180
+ "extractor_reward": 0.0,
181
+ "adversary_reward": 0.0,
182
+ "extractor_elo": 1022.6201387359781,
183
+ "adversary_elo": 1377.3798612640219,
184
+ "edits_applied": 1
185
+ },
186
+ {
187
+ "episode": 23,
188
+ "extractor_reward": 0.0,
189
+ "adversary_reward": 0.0,
190
+ "extractor_elo": 1018.9450393489806,
191
+ "adversary_elo": 1381.0549606510194,
192
+ "edits_applied": 0
193
+ },
194
+ {
195
+ "episode": 24,
196
+ "extractor_reward": 0.0,
197
+ "adversary_reward": 0.0,
198
+ "extractor_elo": 1015.4053522913782,
199
+ "adversary_elo": 1384.5946477086218,
200
+ "edits_applied": 0
201
+ },
202
+ {
203
+ "episode": 25,
204
+ "extractor_reward": 0.0,
205
+ "adversary_reward": 0.0,
206
+ "extractor_elo": 1011.9919376722353,
207
+ "adversary_elo": 1388.0080623277647,
208
+ "edits_applied": 0
209
+ },
210
+ {
211
+ "episode": 26,
212
+ "extractor_reward": 0.0,
213
+ "adversary_reward": 0.0,
214
+ "extractor_elo": 1008.6965169100662,
215
+ "adversary_elo": 1391.303483089934,
216
+ "edits_applied": 1
217
+ },
218
+ {
219
+ "episode": 27,
220
+ "extractor_reward": 0.0,
221
+ "adversary_reward": 0.0,
222
+ "extractor_elo": 1005.5115712470476,
223
+ "adversary_elo": 1394.4884287529526,
224
+ "edits_applied": 0
225
+ },
226
+ {
227
+ "episode": 28,
228
+ "extractor_reward": 0.0,
229
+ "adversary_reward": 0.0,
230
+ "extractor_elo": 1002.43025433112,
231
+ "adversary_elo": 1397.5697456688802,
232
+ "edits_applied": 0
233
+ },
234
+ {
235
+ "episode": 29,
236
+ "extractor_reward": 0.0,
237
+ "adversary_reward": 0.0,
238
+ "extractor_elo": 999.4463166610365,
239
+ "adversary_elo": 1400.5536833389638,
240
+ "edits_applied": 0
241
+ },
242
+ {
243
+ "episode": 30,
244
+ "extractor_reward": 0.0,
245
+ "adversary_reward": 0.0,
246
+ "extractor_elo": 996.5540400688917,
247
+ "adversary_elo": 1403.4459599311085,
248
+ "edits_applied": 1
249
+ },
250
+ {
251
+ "episode": 31,
252
+ "extractor_reward": 0.0,
253
+ "adversary_reward": 0.0,
254
+ "extractor_elo": 993.7481807241646,
255
+ "adversary_elo": 1406.2518192758355,
256
+ "edits_applied": 0
257
+ },
258
+ {
259
+ "episode": 32,
260
+ "extractor_reward": 0.0,
261
+ "adversary_reward": 0.0,
262
+ "extractor_elo": 991.0239193963366,
263
+ "adversary_elo": 1408.9760806036634,
264
+ "edits_applied": 0
265
+ },
266
+ {
267
+ "episode": 33,
268
+ "extractor_reward": 0.0,
269
+ "adversary_reward": 0.0,
270
+ "extractor_elo": 988.3768179205488,
271
+ "adversary_elo": 1411.6231820794512,
272
+ "edits_applied": 1
273
+ },
274
+ {
275
+ "episode": 34,
276
+ "extractor_reward": 0.0,
277
+ "adversary_reward": 0.0,
278
+ "extractor_elo": 985.802780981243,
279
+ "adversary_elo": 1414.197219018757,
280
+ "edits_applied": 1
281
+ },
282
+ {
283
+ "episode": 35,
284
+ "extractor_reward": 0.0,
285
+ "adversary_reward": 0.0,
286
+ "extractor_elo": 983.2980224692853,
287
+ "adversary_elo": 1416.7019775307147,
288
+ "edits_applied": 1
289
+ },
290
+ {
291
+ "episode": 36,
292
+ "extractor_reward": 0.0,
293
+ "adversary_reward": 0.0,
294
+ "extractor_elo": 980.8590357842977,
295
+ "adversary_elo": 1419.1409642157023,
296
+ "edits_applied": 0
297
+ },
298
+ {
299
+ "episode": 37,
300
+ "extractor_reward": 0.0,
301
+ "adversary_reward": 0.0,
302
+ "extractor_elo": 978.4825675503376,
303
+ "adversary_elo": 1421.5174324496625,
304
+ "edits_applied": 0
305
+ },
306
+ {
307
+ "episode": 38,
308
+ "extractor_reward": 0.0,
309
+ "adversary_reward": 0.0,
310
+ "extractor_elo": 976.1655942932874,
311
+ "adversary_elo": 1423.8344057067127,
312
+ "edits_applied": 1
313
+ },
314
+ {
315
+ "episode": 39,
316
+ "extractor_reward": 0.0,
317
+ "adversary_reward": 0.0,
318
+ "extractor_elo": 973.905301695273,
319
+ "adversary_elo": 1426.094698304727,
320
+ "edits_applied": 1
321
+ },
322
+ {
323
+ "episode": 40,
324
+ "extractor_reward": 0.0,
325
+ "adversary_reward": 0.0,
326
+ "extractor_elo": 971.6990660974905,
327
+ "adversary_elo": 1428.3009339025095,
328
+ "edits_applied": 0
329
+ },
330
+ {
331
+ "episode": 41,
332
+ "extractor_reward": 0.0,
333
+ "adversary_reward": 0.0,
334
+ "extractor_elo": 969.5444379698948,
335
+ "adversary_elo": 1430.455562030105,
336
+ "edits_applied": 0
337
+ },
338
+ {
339
+ "episode": 42,
340
+ "extractor_reward": 0.0,
341
+ "adversary_reward": 0.0,
342
+ "extractor_elo": 967.4391271058566,
343
+ "adversary_elo": 1432.5608728941434,
344
+ "edits_applied": 0
345
+ },
346
+ {
347
+ "episode": 43,
348
+ "extractor_reward": 0.0,
349
+ "adversary_reward": 0.0,
350
+ "extractor_elo": 965.380989333385,
351
+ "adversary_elo": 1434.6190106666152,
352
+ "edits_applied": 1
353
+ },
354
+ {
355
+ "episode": 44,
356
+ "extractor_reward": 0.0,
357
+ "adversary_reward": 0.0,
358
+ "extractor_elo": 963.3680145628941,
359
+ "adversary_elo": 1436.6319854371059,
360
+ "edits_applied": 1
361
+ },
362
+ {
363
+ "episode": 45,
364
+ "extractor_reward": 0.0,
365
+ "adversary_reward": 0.0,
366
+ "extractor_elo": 961.3983160155965,
367
+ "adversary_elo": 1438.6016839844035,
368
+ "edits_applied": 0
369
+ },
370
+ {
371
+ "episode": 46,
372
+ "extractor_reward": 0.0,
373
+ "adversary_reward": 0.0,
374
+ "extractor_elo": 959.4701204971408,
375
+ "adversary_elo": 1440.529879502859,
376
+ "edits_applied": 0
377
+ },
378
+ {
379
+ "episode": 47,
380
+ "extractor_reward": 0.0,
381
+ "adversary_reward": 0.0,
382
+ "extractor_elo": 957.5817595986604,
383
+ "adversary_elo": 1442.4182404013395,
384
+ "edits_applied": 0
385
+ },
386
+ {
387
+ "episode": 48,
388
+ "extractor_reward": 0.0,
389
+ "adversary_reward": 0.0,
390
+ "extractor_elo": 955.7316617224171,
391
+ "adversary_elo": 1444.2683382775826,
392
+ "edits_applied": 0
393
+ },
394
+ {
395
+ "episode": 49,
396
+ "extractor_reward": 0.0,
397
+ "adversary_reward": 0.0,
398
+ "extractor_elo": 953.9183448421289,
399
+ "adversary_elo": 1446.081655157871,
400
+ "edits_applied": 1
401
+ },
402
+ {
403
+ "episode": 50,
404
+ "extractor_reward": 0.0,
405
+ "adversary_reward": 0.0,
406
+ "extractor_elo": 952.1404099191716,
407
+ "adversary_elo": 1447.8595900808282,
408
+ "edits_applied": 1
409
+ },
410
+ {
411
+ "episode": 51,
412
+ "extractor_reward": 0.0,
413
+ "adversary_reward": 0.0,
414
+ "extractor_elo": 950.3965349054289,
415
+ "adversary_elo": 1449.6034650945708,
416
+ "edits_applied": 0
417
+ },
418
+ {
419
+ "episode": 52,
420
+ "extractor_reward": 0.0,
421
+ "adversary_reward": 0.0,
422
+ "extractor_elo": 948.685469271849,
423
+ "adversary_elo": 1451.3145307281507,
424
+ "edits_applied": 1
425
+ },
426
+ {
427
+ "episode": 53,
428
+ "extractor_reward": 0.0,
429
+ "adversary_reward": 0.0,
430
+ "extractor_elo": 947.0060290089513,
431
+ "adversary_elo": 1452.9939709910484,
432
+ "edits_applied": 0
433
+ },
434
+ {
435
+ "episode": 54,
436
+ "extractor_reward": 0.0,
437
+ "adversary_reward": 0.0,
438
+ "extractor_elo": 945.3570920517693,
439
+ "adversary_elo": 1454.6429079482302,
440
+ "edits_applied": 1
441
+ },
442
+ {
443
+ "episode": 55,
444
+ "extractor_reward": 0.0,
445
+ "adversary_reward": 0.0,
446
+ "extractor_elo": 943.737594087149,
447
+ "adversary_elo": 1456.2624059128507,
448
+ "edits_applied": 0
449
+ },
450
+ {
451
+ "episode": 56,
452
+ "extractor_reward": 0.0,
453
+ "adversary_reward": 0.0,
454
+ "extractor_elo": 942.146524706064,
455
+ "adversary_elo": 1457.8534752939356,
456
+ "edits_applied": 0
457
+ },
458
+ {
459
+ "episode": 57,
460
+ "extractor_reward": 0.0,
461
+ "adversary_reward": 0.0,
462
+ "extractor_elo": 940.5829238677596,
463
+ "adversary_elo": 1459.41707613224,
464
+ "edits_applied": 0
465
+ },
466
+ {
467
+ "episode": 58,
468
+ "extractor_reward": 0.0,
469
+ "adversary_reward": 0.0,
470
+ "extractor_elo": 939.0458786461639,
471
+ "adversary_elo": 1460.9541213538357,
472
+ "edits_applied": 0
473
+ },
474
+ {
475
+ "episode": 59,
476
+ "extractor_reward": 0.0,
477
+ "adversary_reward": 0.0,
478
+ "extractor_elo": 937.5345202322019,
479
+ "adversary_elo": 1462.465479767798,
480
+ "edits_applied": 1
481
+ },
482
+ {
483
+ "episode": 60,
484
+ "extractor_reward": 0.0,
485
+ "adversary_reward": 0.0,
486
+ "extractor_elo": 936.0480211684466,
487
+ "adversary_elo": 1463.951978831553,
488
+ "edits_applied": 1
489
+ },
490
+ {
491
+ "episode": 61,
492
+ "extractor_reward": 0.0,
493
+ "adversary_reward": 0.0,
494
+ "extractor_elo": 934.585592795019,
495
+ "adversary_elo": 1465.4144072049808,
496
+ "edits_applied": 0
497
+ },
498
+ {
499
+ "episode": 62,
500
+ "extractor_reward": 0.0,
501
+ "adversary_reward": 0.0,
502
+ "extractor_elo": 933.1464828878269,
503
+ "adversary_elo": 1466.853517112173,
504
+ "edits_applied": 0
505
+ },
506
+ {
507
+ "episode": 63,
508
+ "extractor_reward": 0.0,
509
+ "adversary_reward": 0.0,
510
+ "extractor_elo": 931.7299734721649,
511
+ "adversary_elo": 1468.270026527835,
512
+ "edits_applied": 0
513
+ },
514
+ {
515
+ "episode": 64,
516
+ "extractor_reward": 0.0,
517
+ "adversary_reward": 0.0,
518
+ "extractor_elo": 930.335378796408,
519
+ "adversary_elo": 1469.6646212035919,
520
+ "edits_applied": 0
521
+ },
522
+ {
523
+ "episode": 65,
524
+ "extractor_reward": 0.0,
525
+ "adversary_reward": 0.0,
526
+ "extractor_elo": 928.9620434520457,
527
+ "adversary_elo": 1471.037956547954,
528
+ "edits_applied": 0
529
+ },
530
+ {
531
+ "episode": 66,
532
+ "extractor_reward": 0.0,
533
+ "adversary_reward": 0.0,
534
+ "extractor_elo": 927.6093406276557,
535
+ "adversary_elo": 1472.390659372344,
536
+ "edits_applied": 1
537
+ },
538
+ {
539
+ "episode": 67,
540
+ "extractor_reward": 0.0,
541
+ "adversary_reward": 0.0,
542
+ "extractor_elo": 926.2766704856136,
543
+ "adversary_elo": 1473.7233295143863,
544
+ "edits_applied": 1
545
+ },
546
+ {
547
+ "episode": 68,
548
+ "extractor_reward": 0.0,
549
+ "adversary_reward": 0.0,
550
+ "extractor_elo": 924.9634586514076,
551
+ "adversary_elo": 1475.0365413485924,
552
+ "edits_applied": 1
553
+ },
554
+ {
555
+ "episode": 69,
556
+ "extractor_reward": 0.0,
557
+ "adversary_reward": 0.0,
558
+ "extractor_elo": 923.6691548063811,
559
+ "adversary_elo": 1476.3308451936189,
560
+ "edits_applied": 0
561
+ },
562
+ {
563
+ "episode": 70,
564
+ "extractor_reward": 0.0,
565
+ "adversary_reward": 0.0,
566
+ "extractor_elo": 922.3932313755844,
567
+ "adversary_elo": 1477.6067686244157,
568
+ "edits_applied": 1
569
+ },
570
+ {
571
+ "episode": 71,
572
+ "extractor_reward": 0.0,
573
+ "adversary_reward": 0.0,
574
+ "extractor_elo": 921.1351823031758,
575
+ "adversary_elo": 1478.8648176968243,
576
+ "edits_applied": 0
577
+ },
578
+ {
579
+ "episode": 72,
580
+ "extractor_reward": 0.0,
581
+ "adversary_reward": 0.0,
582
+ "extractor_elo": 919.8945219085081,
583
+ "adversary_elo": 1480.105478091492,
584
+ "edits_applied": 0
585
+ },
586
+ {
587
+ "episode": 73,
588
+ "extractor_reward": 0.0,
589
+ "adversary_reward": 0.0,
590
+ "extractor_elo": 918.6707838166437,
591
+ "adversary_elo": 1481.3292161833563,
592
+ "edits_applied": 0
593
+ },
594
+ {
595
+ "episode": 74,
596
+ "extractor_reward": 0.0,
597
+ "adversary_reward": 0.0,
598
+ "extractor_elo": 917.4635199576037,
599
+ "adversary_elo": 1482.5364800423963,
600
+ "edits_applied": 0
601
+ },
602
+ {
603
+ "episode": 75,
604
+ "extractor_reward": 0.0,
605
+ "adversary_reward": 0.0,
606
+ "extractor_elo": 916.2722996291502,
607
+ "adversary_elo": 1483.7277003708498,
608
+ "edits_applied": 0
609
+ },
610
+ {
611
+ "episode": 76,
612
+ "extractor_reward": 0.0,
613
+ "adversary_reward": 0.0,
614
+ "extractor_elo": 915.096708618356,
615
+ "adversary_elo": 1484.903291381644,
616
+ "edits_applied": 1
617
+ },
618
+ {
619
+ "episode": 77,
620
+ "extractor_reward": 0.0,
621
+ "adversary_reward": 0.0,
622
+ "extractor_elo": 913.9363483776176,
623
+ "adversary_elo": 1486.0636516223824,
624
+ "edits_applied": 0
625
+ },
626
+ {
627
+ "episode": 78,
628
+ "extractor_reward": 0.0,
629
+ "adversary_reward": 0.0,
630
+ "extractor_elo": 912.7908352511389,
631
+ "adversary_elo": 1487.2091647488612,
632
+ "edits_applied": 1
633
+ },
634
+ {
635
+ "episode": 79,
636
+ "extractor_reward": 0.0,
637
+ "adversary_reward": 0.0,
638
+ "extractor_elo": 911.6597997482429,
639
+ "adversary_elo": 1488.340200251757,
640
+ "edits_applied": 0
641
+ },
642
+ {
643
+ "episode": 80,
644
+ "extractor_reward": 0.0,
645
+ "adversary_reward": 0.0,
646
+ "extractor_elo": 910.5428858601717,
647
+ "adversary_elo": 1489.4571141398283,
648
+ "edits_applied": 0
649
+ },
650
+ {
651
+ "episode": 81,
652
+ "extractor_reward": 0.0,
653
+ "adversary_reward": 0.0,
654
+ "extractor_elo": 909.4397504173062,
655
+ "adversary_elo": 1490.5602495826938,
656
+ "edits_applied": 1
657
+ },
658
+ {
659
+ "episode": 82,
660
+ "extractor_reward": 0.0,
661
+ "adversary_reward": 0.0,
662
+ "extractor_elo": 908.3500624839869,
663
+ "adversary_elo": 1491.649937516013,
664
+ "edits_applied": 0
665
+ },
666
+ {
667
+ "episode": 83,
668
+ "extractor_reward": 0.0,
669
+ "adversary_reward": 0.0,
670
+ "extractor_elo": 907.2735027883432,
671
+ "adversary_elo": 1492.7264972116568,
672
+ "edits_applied": 1
673
+ },
674
+ {
675
+ "episode": 84,
676
+ "extractor_reward": 0.0,
677
+ "adversary_reward": 0.0,
678
+ "extractor_elo": 906.2097631847404,
679
+ "adversary_elo": 1493.7902368152595,
680
+ "edits_applied": 0
681
+ },
682
+ {
683
+ "episode": 85,
684
+ "extractor_reward": 0.0,
685
+ "adversary_reward": 0.0,
686
+ "extractor_elo": 905.1585461466454,
687
+ "adversary_elo": 1494.8414538533546,
688
+ "edits_applied": 1
689
+ },
690
+ {
691
+ "episode": 86,
692
+ "extractor_reward": 0.0,
693
+ "adversary_reward": 0.0,
694
+ "extractor_elo": 904.1195642878787,
695
+ "adversary_elo": 1495.8804357121212,
696
+ "edits_applied": 0
697
+ },
698
+ {
699
+ "episode": 87,
700
+ "extractor_reward": 0.0,
701
+ "adversary_reward": 0.0,
702
+ "extractor_elo": 903.0925399103778,
703
+ "adversary_elo": 1496.907460089622,
704
+ "edits_applied": 0
705
+ },
706
+ {
707
+ "episode": 88,
708
+ "extractor_reward": 0.0,
709
+ "adversary_reward": 0.0,
710
+ "extractor_elo": 902.07720457674,
711
+ "adversary_elo": 1497.9227954232597,
712
+ "edits_applied": 0
713
+ },
714
+ {
715
+ "episode": 89,
716
+ "extractor_reward": 0.0,
717
+ "adversary_reward": 0.0,
718
+ "extractor_elo": 901.0732987059399,
719
+ "adversary_elo": 1498.9267012940597,
720
+ "edits_applied": 1
721
+ },
722
+ {
723
+ "episode": 90,
724
+ "extractor_reward": 0.0,
725
+ "adversary_reward": 0.0,
726
+ "extractor_elo": 900.0805711907396,
727
+ "adversary_elo": 1499.91942880926,
728
+ "edits_applied": 1
729
+ },
730
+ {
731
+ "episode": 91,
732
+ "extractor_reward": 0.0,
733
+ "adversary_reward": 0.0,
734
+ "extractor_elo": 899.0987790354162,
735
+ "adversary_elo": 1500.9012209645832,
736
+ "edits_applied": 1
737
+ },
738
+ {
739
+ "episode": 92,
740
+ "extractor_reward": 0.0,
741
+ "adversary_reward": 0.0,
742
+ "extractor_elo": 898.1276870125314,
743
+ "adversary_elo": 1501.8723129874681,
744
+ "edits_applied": 1
745
+ },
746
+ {
747
+ "episode": 93,
748
+ "extractor_reward": 0.0,
749
+ "adversary_reward": 0.0,
750
+ "extractor_elo": 897.167067337562,
751
+ "adversary_elo": 1502.8329326624375,
752
+ "edits_applied": 0
753
+ },
754
+ {
755
+ "episode": 94,
756
+ "extractor_reward": 0.0,
757
+ "adversary_reward": 0.0,
758
+ "extractor_elo": 896.2166993602922,
759
+ "adversary_elo": 1503.7833006397072,
760
+ "edits_applied": 0
761
+ },
762
+ {
763
+ "episode": 95,
764
+ "extractor_reward": 0.0,
765
+ "adversary_reward": 0.0,
766
+ "extractor_elo": 895.2763692719469,
767
+ "adversary_elo": 1504.7236307280525,
768
+ "edits_applied": 0
769
+ },
770
+ {
771
+ "episode": 96,
772
+ "extractor_reward": 0.0,
773
+ "adversary_reward": 0.0,
774
+ "extractor_elo": 894.3458698271176,
775
+ "adversary_elo": 1505.6541301728819,
776
+ "edits_applied": 0
777
+ },
778
+ {
779
+ "episode": 97,
780
+ "extractor_reward": 0.0,
781
+ "adversary_reward": 0.0,
782
+ "extractor_elo": 893.4250000795969,
783
+ "adversary_elo": 1506.5749999204027,
784
+ "edits_applied": 1
785
+ },
786
+ {
787
+ "episode": 98,
788
+ "extractor_reward": 0.0,
789
+ "adversary_reward": 0.0,
790
+ "extractor_elo": 892.5135651312996,
791
+ "adversary_elo": 1507.4864348687,
792
+ "edits_applied": 1
793
+ },
794
+ {
795
+ "episode": 99,
796
+ "extractor_reward": 0.0,
797
+ "adversary_reward": 0.0,
798
+ "extractor_elo": 891.6113758935032,
799
+ "adversary_elo": 1508.3886241064963,
800
+ "edits_applied": 0
801
+ }
802
+ ]