Per-iteration adversarial training progress
Here we show games from each iteration of our iterated adversarial training procedure. At each iteration, the victim vn is generated by fine-tuning the previous victim vn-1 against the previous adversary an-1, and the adversary an is generated by fine-tuning the previous adversary an-1 against the victim vn. The initial victim v0 is KataGo network checkpoint b40c256-s11840935168-d2898845681, the network we attacked with our original cyclic adversary (base-adversary). The initial adversary a0 is the original cyclic adversary.
a0 vs. v0
Against victim v0, a0 achieves win rates of 100% at 16 victim visits, 99% at 256 visits, and 99% at 4096 visits.
Victim: v0, 16 visits
Adversary: a0
a0 vs. v1
Against victim v1, a0 achieves win rates of 13% at 16 victim visits, 1% at 256 visits, and 1% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -53.0
Victim: v1, 16 visits
Adversary: a0
a1 vs. v1
Against victim v1, a1 achieves win rates of 99% at 16 victim visits, 86% at 256 visits, and 69% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -22.7
Victim: v1, 16 visits
Adversary: a1
a1 vs. v2
Against victim v2, a1 achieves win rates of 34% at 16 victim visits, 4% at 256 visits, and 0% at 4096 visits.
adversary predicted win prob: 1.00 loss: 0.00, predicted score: 68.5
Victim: v2, 16 visits
Adversary: a1
a2 vs. v2
Against victim v2, a2 achieves win rates of 99% at 16 victim visits, 95% at 256 visits, and 56% at 4096 visits.
adversary predicted win prob: 1.00 loss: 0.00, predicted score: 210.6
Victim: v2, 16 visits
Adversary: a2
a2 vs. v3
Against victim v3, a2 achieves win rates of 13% at 16 victim visits, 4% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -176.5
Victim: v3, 16 visits
Adversary: a2
a3 vs. v3
Against victim v3, a3 achieves win rates of 88% at 16 victim visits, 67% at 256 visits, and 33% at 4096 visits.
adversary predicted win prob: 1.00 loss: 0.00, predicted score: 52.3
Victim: v3, 16 visits
Adversary: a3
a3 vs. v4
Against victim v4, a3 achieves win rates of 18% at 16 victim visits, 0% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -10.0
Victim: v4, 16 visits
Adversary: a3
a4 vs. v4
Against victim v4, a4 achieves win rates of 94% at 16 victim visits, 54% at 256 visits, and 25% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -14.3
Victim: v4, 16 visits
Adversary: a4
a4 vs. v5
Against victim v5, a4 achieves win rates of 9% at 16 victim visits, 0% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -23.0
Victim: v5, 16 visits
Adversary: a4
a5 vs. v5
Against victim v5, a5 achieves win rates of 51% at 16 victim visits, 3% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -12.1
Victim: v5, 16 visits
Adversary: a5
a5 vs. v6
Against victim v6, a5 achieves win rates of 10% at 16 victim visits, 1% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -6.6
Victim: v6, 16 visits
Adversary: a5
a6 vs. v6
Against victim v6, a6 achieves win rates of 38% at 16 victim visits, 9% at 256 visits, and 2% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -17.4
Victim: v6, 16 visits
Adversary: a6
a6 vs. v7
Against victim v7, a6 achieves win rates of 26% at 16 victim visits, 1% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -10.6
Victim: v7, 16 visits
Adversary: a6
a7 vs. v7
Against victim v7, a7 achieves win rates of 94% at 16 victim visits, 47% at 256 visits, and 32% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -38.6
Victim: v7, 16 visits
Adversary: a7
a7 vs. v8
Against victim v8, a7 achieves win rates of 16% at 16 victim visits, 0% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -34.9
Victim: v8, 16 visits
Adversary: a7
a8 vs. v8
Against victim v8, a8 achieves win rates of 24% at 16 victim visits, 0% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -21.0
Victim: v8, 16 visits
Adversary: a8
a8 vs. v9
Against victim v9, a8 achieves win rates of 6% at 16 victim visits, 2% at 256 visits, and 0% at 4096 visits.
victim predicted win prob: 1.00 loss: 0.00, predicted score: 366.5
Victim: v9, 16 visits
Adversary: a8
a9 vs. v9
Against victim v9, a9 achieves win rates of 99% at 16 victim visits, 94% at 256 visits, and 59% at 4096 visits.
victim predicted win prob: 0.00 loss: 1.00, predicted score: -60.1
Victim: v9, 16 visits
Adversary: a9
victim predicted win prob: 0.00 loss: 1.00, predicted score: -108.2