jalf/TIR_PROJ
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
a561f8a6970f1fbbfd8f82c11e854562ceddbc78
TIR_PROJ/training/runs/v1.log
T
Johnny Fernandes acf0810425 Test26_1200
2026-04-26 11:04:23 +00:00

243 lines
19 KiB
Plaintext
Raw Blame History

Config loaded from config.json
Config: {'W_PER_SHEEP': 2.0, 'W_ALIGN': 0.05, 'W_PEN_BONUS': 10.0, 'W_COMPLETE': 100.0, 'W_STEP_COST': 0.02, 'W_COMPACT': 0.0, 'W_WALL_TOUCH': 0.01, 'WALL_TOUCH_BUFFER': 0.4, 'ALIGN_SHAPE': 'standoff', 'ALIGN_GATED': True, 'ENTRY_AWARE': True, 'ent_coef': 0.02}
Run dir: runs/v1
Curriculum: 1 → 10 sheep, 1,500,000 steps/stage
[Stage n_sheep=1] training 1,500,000 steps
... [1 sheep | 100,000 steps | ret(last 40)=-19.52 win_sr=2% cum_sr=2%]
... [1 sheep | 200,000 steps | ret(last 50)=-21.11 win_sr=4% cum_sr=4%]
... [1 sheep | 300,000 steps | ret(last 50)=-7.06 win_sr=12% cum_sr=7%]
... [1 sheep | 400,000 steps | ret(last 50)=+18.18 win_sr=90% cum_sr=40%]
... [1 sheep | 500,000 steps | ret(last 50)=+16.17 win_sr=100% cum_sr=69%]
... [1 sheep | 600,000 steps | ret(last 50)=+14.68 win_sr=100% cum_sr=82%]
... [1 sheep | 700,000 steps | ret(last 50)=+14.33 win_sr=100% cum_sr=88%]
... [1 sheep | 800,000 steps | ret(last 50)=+14.20 win_sr=100% cum_sr=91%]
... [1 sheep | 900,000 steps | ret(last 50)=+13.82 win_sr=100% cum_sr=93%]
... [1 sheep | 1,000,000 steps | ret(last 50)=+13.76 win_sr=100% cum_sr=94%]
... [1 sheep | 1,100,000 steps | ret(last 50)=+13.72 win_sr=100% cum_sr=95%]
... [1 sheep | 1,200,000 steps | ret(last 50)=+13.41 win_sr=100% cum_sr=95%]
... [1 sheep | 1,300,000 steps | ret(last 50)=+13.42 win_sr=100% cum_sr=96%]
... [1 sheep | 1,400,000 steps | ret(last 50)=+13.40 win_sr=100% cum_sr=96%]
... [1 sheep | 1,500,000 steps | ret(last 50)=+13.24 win_sr=100% cum_sr=97%]
[Stage n_sheep=1] evaluating 30 eps
[Stage n_sheep=1] sr=100% mean_len=243 mean_min_pen=3.7m mean_act=0.39
failure modes: SUCCESS=30
reward/step: progress=+0.1141 alignment=+0.0003 compact=+0.0000 wall_touch=+0.0000 pen_bonus=+0.0412 step_cost=-0.0200 complete=+0.4115
[Stage n_sheep=2] training 1,500,000 steps
... [2 sheep | 1,507,336 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [2 sheep | 1,607,336 steps | ret(last 42)=-4.07 win_sr=7% cum_sr=7%]
... [2 sheep | 1,707,336 steps | ret(last 50)=-6.10 win_sr=0% cum_sr=4%]
... [2 sheep | 1,807,336 steps | ret(last 50)=-5.57 win_sr=2% cum_sr=3%]
... [2 sheep | 1,907,336 steps | ret(last 50)=-5.04 win_sr=4% cum_sr=4%]
... [2 sheep | 2,007,336 steps | ret(last 50)=-4.27 win_sr=10% cum_sr=5%]
... [2 sheep | 2,107,336 steps | ret(last 50)=-4.42 win_sr=6% cum_sr=5%]
... [2 sheep | 2,207,336 steps | ret(last 50)=+4.57 win_sr=50% cum_sr=13%]
... [2 sheep | 2,307,336 steps | ret(last 50)=+11.35 win_sr=70% cum_sr=24%]
... [2 sheep | 2,407,336 steps | ret(last 50)=+15.75 win_sr=86% cum_sr=32%]
... [2 sheep | 2,507,336 steps | ret(last 50)=+19.97 win_sr=100% cum_sr=44%]
... [2 sheep | 2,607,336 steps | ret(last 50)=+20.73 win_sr=100% cum_sr=54%]
... [2 sheep | 2,707,336 steps | ret(last 50)=+19.81 win_sr=100% cum_sr=62%]
... [2 sheep | 2,807,336 steps | ret(last 50)=+20.83 win_sr=100% cum_sr=67%]
... [2 sheep | 2,907,336 steps | ret(last 50)=+20.43 win_sr=100% cum_sr=72%]
... [2 sheep | 3,007,336 steps | ret(last 50)=+19.65 win_sr=100% cum_sr=75%]
[Stage n_sheep=2] evaluating 30 eps
[Stage n_sheep=2] sr=63% mean_len=1325 mean_min_pen=3.1m mean_act=0.42
failure modes: SUCCESS=19 PARTIAL_1of2=10 COMPACT_CANT_DRIVE=1
reward/step: progress=+0.0453 alignment=+0.0065 compact=+0.0000 wall_touch=-0.0052 pen_bonus=+0.0123 step_cost=-0.0200 complete=+0.0478
[Stage n_sheep=3] training 1,500,000 steps
... [3 sheep | 3,014,664 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [3 sheep | 3,114,664 steps | ret(last 50)=+28.02 win_sr=100% cum_sr=100%]
... [3 sheep | 3,214,664 steps | ret(last 50)=+24.04 win_sr=96% cum_sr=99%]
... [3 sheep | 3,314,664 steps | ret(last 50)=+27.02 win_sr=100% cum_sr=99%]
... [3 sheep | 3,414,664 steps | ret(last 50)=+25.53 win_sr=100% cum_sr=99%]
... [3 sheep | 3,514,664 steps | ret(last 50)=+25.13 win_sr=96% cum_sr=99%]
... [3 sheep | 3,614,664 steps | ret(last 50)=+26.45 win_sr=100% cum_sr=99%]
... [3 sheep | 3,714,664 steps | ret(last 50)=+25.83 win_sr=100% cum_sr=99%]
... [3 sheep | 3,814,664 steps | ret(last 50)=+26.07 win_sr=100% cum_sr=99%]
... [3 sheep | 3,914,664 steps | ret(last 50)=+25.03 win_sr=96% cum_sr=99%]
... [3 sheep | 4,014,664 steps | ret(last 50)=+24.53 win_sr=98% cum_sr=99%]
... [3 sheep | 4,114,664 steps | ret(last 50)=+24.98 win_sr=100% cum_sr=99%]
... [3 sheep | 4,214,664 steps | ret(last 50)=+26.81 win_sr=100% cum_sr=99%]
... [3 sheep | 4,314,664 steps | ret(last 50)=+24.78 win_sr=98% cum_sr=99%]
... [3 sheep | 4,414,664 steps | ret(last 50)=+26.79 win_sr=100% cum_sr=99%]
... [3 sheep | 4,514,664 steps | ret(last 50)=+26.26 win_sr=100% cum_sr=99%]
[Stage n_sheep=3] evaluating 30 eps
[Stage n_sheep=3] sr=97% mean_len=828 mean_min_pen=2.7m mean_act=1.15
failure modes: SUCCESS=29 PARTIAL_1of3=1
reward/step: progress=+0.1017 alignment=+0.0139 compact=+0.0000 wall_touch=-0.0023 pen_bonus=+0.0354 step_cost=-0.0200 complete=+0.1168
[Stage n_sheep=4] training 1,500,000 steps
... [4 sheep | 4,521,992 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [4 sheep | 4,621,992 steps | ret(last 50)=+28.27 win_sr=90% cum_sr=93%]
... [4 sheep | 4,721,992 steps | ret(last 50)=+31.16 win_sr=98% cum_sr=95%]
... [4 sheep | 4,821,992 steps | ret(last 50)=+30.45 win_sr=100% cum_sr=96%]
... [4 sheep | 4,921,992 steps | ret(last 50)=+31.12 win_sr=100% cum_sr=96%]
... [4 sheep | 5,021,992 steps | ret(last 50)=+30.78 win_sr=100% cum_sr=97%]
... [4 sheep | 5,121,992 steps | ret(last 50)=+30.42 win_sr=100% cum_sr=97%]
... [4 sheep | 5,221,992 steps | ret(last 50)=+31.14 win_sr=100% cum_sr=98%]
... [4 sheep | 5,321,992 steps | ret(last 50)=+31.20 win_sr=100% cum_sr=98%]
... [4 sheep | 5,421,992 steps | ret(last 50)=+30.47 win_sr=98% cum_sr=98%]
... [4 sheep | 5,521,992 steps | ret(last 50)=+30.13 win_sr=100% cum_sr=98%]
... [4 sheep | 5,621,992 steps | ret(last 50)=+28.52 win_sr=98% cum_sr=98%]
... [4 sheep | 5,721,992 steps | ret(last 50)=+31.40 win_sr=100% cum_sr=98%]
... [4 sheep | 5,821,992 steps | ret(last 50)=+30.30 win_sr=100% cum_sr=99%]
... [4 sheep | 5,921,992 steps | ret(last 50)=+29.45 win_sr=100% cum_sr=99%]
... [4 sheep | 6,021,992 steps | ret(last 50)=+30.26 win_sr=100% cum_sr=99%]
[Stage n_sheep=4] evaluating 30 eps
[Stage n_sheep=4] sr=57% mean_len=1686 mean_min_pen=1.8m mean_act=1.01
failure modes: SUCCESS=17 PARTIAL_1of4=10 PARTIAL_2of4=3
reward/step: progress=+0.0721 alignment=+0.0085 compact=+0.0000 wall_touch=-0.0110 pen_bonus=+0.0166 step_cost=-0.0200 complete=+0.0336
[Stage n_sheep=5] training 1,500,000 steps
... [5 sheep | 6,029,320 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [5 sheep | 6,129,320 steps | ret(last 50)=+34.59 win_sr=100% cum_sr=100%]
... [5 sheep | 6,229,320 steps | ret(last 50)=+35.53 win_sr=100% cum_sr=100%]
... [5 sheep | 6,329,320 steps | ret(last 50)=+34.77 win_sr=100% cum_sr=100%]
... [5 sheep | 6,429,320 steps | ret(last 50)=+34.30 win_sr=100% cum_sr=100%]
... [5 sheep | 6,529,320 steps | ret(last 50)=+35.12 win_sr=100% cum_sr=100%]
... [5 sheep | 6,629,320 steps | ret(last 50)=+33.76 win_sr=100% cum_sr=100%]
... [5 sheep | 6,729,320 steps | ret(last 50)=+34.81 win_sr=100% cum_sr=100%]
... [5 sheep | 6,829,320 steps | ret(last 50)=+31.82 win_sr=100% cum_sr=100%]
... [5 sheep | 6,929,320 steps | ret(last 50)=+33.69 win_sr=98% cum_sr=100%]
... [5 sheep | 7,029,320 steps | ret(last 50)=+31.65 win_sr=100% cum_sr=100%]
... [5 sheep | 7,129,320 steps | ret(last 50)=+31.83 win_sr=96% cum_sr=99%]
... [5 sheep | 7,229,320 steps | ret(last 50)=+33.96 win_sr=100% cum_sr=99%]
... [5 sheep | 7,329,320 steps | ret(last 50)=+33.65 win_sr=98% cum_sr=99%]
... [5 sheep | 7,429,320 steps | ret(last 50)=+34.20 win_sr=100% cum_sr=99%]
... [5 sheep | 7,529,320 steps | ret(last 50)=+35.27 win_sr=98% cum_sr=99%]
[Stage n_sheep=5] evaluating 30 eps
[Stage n_sheep=5] sr=63% mean_len=1654 mean_min_pen=1.6m mean_act=1.36
failure modes: SUCCESS=19 PARTIAL_2of5=9 PARTIAL_3of5=2
reward/step: progress=+0.1043 alignment=+0.0108 compact=+0.0000 wall_touch=-0.0100 pen_bonus=+0.0240 step_cost=-0.0200 complete=+0.0383
[Stage n_sheep=6] training 1,500,000 steps
... [6 sheep | 7,536,648 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [6 sheep | 7,636,648 steps | ret(last 50)=+37.79 win_sr=98% cum_sr=95%]
... [6 sheep | 7,736,648 steps | ret(last 50)=+38.87 win_sr=94% cum_sr=95%]
... [6 sheep | 7,836,648 steps | ret(last 50)=+37.50 win_sr=98% cum_sr=96%]
... [6 sheep | 7,936,648 steps | ret(last 50)=+39.42 win_sr=94% cum_sr=96%]
... [6 sheep | 8,036,648 steps | ret(last 50)=+38.28 win_sr=98% cum_sr=96%]
... [6 sheep | 8,136,648 steps | ret(last 50)=+36.39 win_sr=100% cum_sr=97%]
... [6 sheep | 8,236,648 steps | ret(last 50)=+39.29 win_sr=100% cum_sr=97%]
... [6 sheep | 8,336,648 steps | ret(last 50)=+37.92 win_sr=98% cum_sr=97%]
... [6 sheep | 8,436,648 steps | ret(last 50)=+38.64 win_sr=98% cum_sr=97%]
... [6 sheep | 8,536,648 steps | ret(last 50)=+38.46 win_sr=98% cum_sr=97%]
... [6 sheep | 8,636,648 steps | ret(last 50)=+38.08 win_sr=98% cum_sr=97%]
... [6 sheep | 8,736,648 steps | ret(last 50)=+36.78 win_sr=100% cum_sr=97%]
... [6 sheep | 8,836,648 steps | ret(last 50)=+36.81 win_sr=98% cum_sr=98%]
... [6 sheep | 8,936,648 steps | ret(last 50)=+37.89 win_sr=98% cum_sr=98%]
... [6 sheep | 9,036,648 steps | ret(last 50)=+36.17 win_sr=98% cum_sr=98%]
[Stage n_sheep=6] evaluating 30 eps
[Stage n_sheep=6] sr=33% mean_len=2161 mean_min_pen=1.8m mean_act=1.37
failure modes: PARTIAL_5of6=14 SUCCESS=10 PARTIAL_4of6=4 COMPACT_CANT_DRIVE=2
reward/step: progress=+0.0915 alignment=+0.0102 compact=+0.0000 wall_touch=-0.0068 pen_bonus=+0.0225 step_cost=-0.0200 complete=+0.0154
[Stage n_sheep=7] training 1,500,000 steps
... [7 sheep | 9,043,976 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [7 sheep | 9,143,976 steps | ret(last 50)=+39.61 win_sr=98% cum_sr=97%]
... [7 sheep | 9,243,976 steps | ret(last 50)=+42.39 win_sr=100% cum_sr=99%]
... [7 sheep | 9,343,976 steps | ret(last 50)=+39.89 win_sr=96% cum_sr=98%]
... [7 sheep | 9,443,976 steps | ret(last 50)=+42.48 win_sr=98% cum_sr=98%]
... [7 sheep | 9,543,976 steps | ret(last 50)=+39.16 win_sr=98% cum_sr=98%]
... [7 sheep | 9,643,976 steps | ret(last 50)=+38.80 win_sr=96% cum_sr=98%]
... [7 sheep | 9,743,976 steps | ret(last 50)=+43.06 win_sr=96% cum_sr=98%]
... [7 sheep | 9,843,976 steps | ret(last 50)=+40.04 win_sr=94% cum_sr=98%]
... [7 sheep | 9,943,976 steps | ret(last 50)=+40.45 win_sr=98% cum_sr=97%]
... [7 sheep | 10,043,976 steps | ret(last 50)=+39.21 win_sr=96% cum_sr=97%]
... [7 sheep | 10,143,976 steps | ret(last 50)=+40.23 win_sr=100% cum_sr=97%]
... [7 sheep | 10,243,976 steps | ret(last 50)=+41.51 win_sr=96% cum_sr=97%]
... [7 sheep | 10,343,976 steps | ret(last 50)=+40.05 win_sr=98% cum_sr=97%]
... [7 sheep | 10,443,976 steps | ret(last 50)=+39.17 win_sr=96% cum_sr=97%]
... [7 sheep | 10,543,976 steps | ret(last 50)=+41.80 win_sr=98% cum_sr=97%]
[Stage n_sheep=7] evaluating 30 eps
[Stage n_sheep=7] sr=20% mean_len=2211 mean_min_pen=1.8m mean_act=1.36
failure modes: PARTIAL_4of7=11 PARTIAL_3of7=8 SUCCESS=6 PARTIAL_6of7=3 PARTIAL_5of7=2
reward/step: progress=+0.0879 alignment=+0.0086 compact=+0.0000 wall_touch=-0.0142 pen_bonus=+0.0208 step_cost=-0.0200 complete=+0.0090
[Stage n_sheep=8] training 1,500,000 steps
... [8 sheep | 10,551,304 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [8 sheep | 10,651,304 steps | ret(last 50)=+48.67 win_sr=96% cum_sr=97%]
... [8 sheep | 10,751,304 steps | ret(last 50)=+46.60 win_sr=96% cum_sr=97%]
... [8 sheep | 10,851,304 steps | ret(last 50)=+41.39 win_sr=98% cum_sr=96%]
... [8 sheep | 10,951,304 steps | ret(last 50)=+41.47 win_sr=96% cum_sr=96%]
... [8 sheep | 11,051,304 steps | ret(last 50)=+40.29 win_sr=96% cum_sr=95%]
... [8 sheep | 11,151,304 steps | ret(last 50)=+42.96 win_sr=100% cum_sr=96%]
... [8 sheep | 11,251,304 steps | ret(last 50)=+42.87 win_sr=94% cum_sr=96%]
... [8 sheep | 11,351,304 steps | ret(last 50)=+44.71 win_sr=100% cum_sr=96%]
... [8 sheep | 11,451,304 steps | ret(last 50)=+45.20 win_sr=96% cum_sr=96%]
... [8 sheep | 11,551,304 steps | ret(last 50)=+46.82 win_sr=96% cum_sr=96%]
... [8 sheep | 11,651,304 steps | ret(last 50)=+43.23 win_sr=96% cum_sr=96%]
... [8 sheep | 11,751,304 steps | ret(last 50)=+43.77 win_sr=94% cum_sr=96%]
... [8 sheep | 11,851,304 steps | ret(last 50)=+48.78 win_sr=98% cum_sr=96%]
... [8 sheep | 11,951,304 steps | ret(last 50)=+43.19 win_sr=94% cum_sr=96%]
... [8 sheep | 12,051,304 steps | ret(last 50)=+42.83 win_sr=96% cum_sr=96%]
[Stage n_sheep=8] evaluating 30 eps
[Stage n_sheep=8] sr=63% mean_len=1745 mean_min_pen=1.7m mean_act=1.37
failure modes: SUCCESS=19 PARTIAL_4of8=9 PARTIAL_1of8=1 PARTIAL_6of8=1
reward/step: progress=+0.1198 alignment=+0.0134 compact=+0.0000 wall_touch=-0.0107 pen_bonus=+0.0373 step_cost=-0.0200 complete=+0.0363
[Stage n_sheep=9] training 1,500,000 steps
... [9 sheep | 12,058,632 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [9 sheep | 12,158,632 steps | ret(last 50)=+49.04 win_sr=98% cum_sr=97%]
... [9 sheep | 12,258,632 steps | ret(last 50)=+47.01 win_sr=96% cum_sr=97%]
... [9 sheep | 12,358,632 steps | ret(last 50)=+48.47 win_sr=90% cum_sr=95%]
... [9 sheep | 12,458,632 steps | ret(last 50)=+46.43 win_sr=88% cum_sr=94%]
... [9 sheep | 12,558,632 steps | ret(last 50)=+44.78 win_sr=94% cum_sr=94%]
... [9 sheep | 12,658,632 steps | ret(last 50)=+49.15 win_sr=100% cum_sr=95%]
... [9 sheep | 12,758,632 steps | ret(last 50)=+47.87 win_sr=94% cum_sr=95%]
... [9 sheep | 12,858,632 steps | ret(last 50)=+50.32 win_sr=96% cum_sr=95%]
... [9 sheep | 12,958,632 steps | ret(last 50)=+47.07 win_sr=94% cum_sr=95%]
... [9 sheep | 13,058,632 steps | ret(last 50)=+48.71 win_sr=100% cum_sr=96%]
... [9 sheep | 13,158,632 steps | ret(last 50)=+47.69 win_sr=96% cum_sr=96%]
... [9 sheep | 13,258,632 steps | ret(last 50)=+46.83 win_sr=98% cum_sr=96%]
... [9 sheep | 13,358,632 steps | ret(last 50)=+48.27 win_sr=94% cum_sr=96%]
... [9 sheep | 13,458,632 steps | ret(last 50)=+47.61 win_sr=88% cum_sr=95%]
... [9 sheep | 13,558,632 steps | ret(last 50)=+47.29 win_sr=96% cum_sr=95%]
[Stage n_sheep=9] evaluating 30 eps
[Stage n_sheep=9] sr=83% mean_len=1723 mean_min_pen=1.8m mean_act=1.38
failure modes: SUCCESS=25 PARTIAL_5of9=3 NEVER_COMPACT=1 PARTIAL_6of9=1
reward/step: progress=+0.1562 alignment=+0.0155 compact=+0.0000 wall_touch=-0.0073 pen_bonus=+0.0480 step_cost=-0.0200 complete=+0.0484
[Stage n_sheep=10] training 1,500,000 steps
... [10 sheep | 13,565,960 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [10 sheep | 13,665,960 steps | ret(last 50)=+50.02 win_sr=94% cum_sr=95%]
... [10 sheep | 13,765,960 steps | ret(last 50)=+48.46 win_sr=84% cum_sr=90%]
... [10 sheep | 13,865,960 steps | ret(last 50)=+48.24 win_sr=84% cum_sr=87%]
... [10 sheep | 13,965,960 steps | ret(last 50)=+50.64 win_sr=82% cum_sr=86%]
... [10 sheep | 14,065,960 steps | ret(last 50)=+53.92 win_sr=86% cum_sr=86%]
... [10 sheep | 14,165,960 steps | ret(last 50)=+51.33 win_sr=80% cum_sr=85%]
... [10 sheep | 14,265,960 steps | ret(last 50)=+49.55 win_sr=76% cum_sr=84%]
... [10 sheep | 14,365,960 steps | ret(last 50)=+51.05 win_sr=92% cum_sr=85%]
... [10 sheep | 14,465,960 steps | ret(last 50)=+47.58 win_sr=86% cum_sr=85%]
... [10 sheep | 14,565,960 steps | ret(last 50)=+47.98 win_sr=74% cum_sr=84%]
... [10 sheep | 14,665,960 steps | ret(last 50)=+50.60 win_sr=82% cum_sr=84%]
... [10 sheep | 14,765,960 steps | ret(last 50)=+51.25 win_sr=88% cum_sr=84%]
... [10 sheep | 14,865,960 steps | ret(last 50)=+50.54 win_sr=92% cum_sr=85%]
... [10 sheep | 14,965,960 steps | ret(last 50)=+50.94 win_sr=92% cum_sr=86%]
... [10 sheep | 15,065,960 steps | ret(last 50)=+50.54 win_sr=90% cum_sr=86%]
[Stage n_sheep=10] evaluating 30 eps
[Stage n_sheep=10] sr=27% mean_len=2267 mean_min_pen=2.2m mean_act=1.38
failure modes: PARTIAL_6of10=16 SUCCESS=8 COMPACT_CANT_DRIVE=2 PARTIAL_7of10=1 PARTIAL_9of10=1 PARTIAL_5of10=1 PARTIAL_8of10=1
reward/step: progress=+0.1360 alignment=+0.0134 compact=+0.0000 wall_touch=-0.0122 pen_bonus=+0.0301 step_cost=-0.0200 complete=+0.0118
======================================================================
TRAINING SUMMARY
======================================================================
n_sheep=1 sr=100% len= 243 min_pen= 3.7m act=0.39
n_sheep=2 sr= 63% len= 1325 min_pen= 3.1m act=0.42
n_sheep=3 sr= 97% len= 828 min_pen= 2.7m act=1.15
n_sheep=4 sr= 57% len= 1686 min_pen= 1.8m act=1.01
n_sheep=5 sr= 63% len= 1654 min_pen= 1.6m act=1.36
n_sheep=6 sr= 33% len= 2161 min_pen= 1.8m act=1.37
n_sheep=7 sr= 20% len= 2211 min_pen= 1.8m act=1.36
n_sheep=8 sr= 63% len= 1745 min_pen= 1.7m act=1.37
n_sheep=9 sr= 83% len= 1723 min_pen= 1.8m act=1.38
n_sheep=10 sr= 27% len= 2267 min_pen= 2.2m act=1.38
Total time: 97.6 min
Artefacts: runs/v1/
Plots: runs/v1/success_rate.png, runs/v1/eval/
Reference in New Issue View Git Blame Copy Permalink