jalf/TIR_PROJ
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Test25_2330

Browse Source
This commit is contained in:
Johnny Fernandes
2026-04-25 22:32:06 +00:00
parent 7b87908410
commit 6612dbc1ba
5 changed files with 336 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files
training/runs/final_v3.log
+253
View File
@@ -0,0 +1,253 @@
Config: {'W_PER_SHEEP': 1.0, 'W_ALIGN': 0.0, 'W_PEN_BONUS': 5.0, 'W_STEP_COST': 0.02, 'W_COMPLETE': 200.0, 'W_COMPACT': 1.5, 'ALIGN_SHAPE': 'standoff', 'ALIGN_GATED': False, 'ent_coef': 0.02}
Run dir: runs/final_v3
Curriculum: 1 → 10 sheep, 1,500,000 steps/stage
[Stage n_sheep=1] training 1,500,000 steps
... [trial 1 | 1 sheep | 100,000 steps | ret(last 40)=-28.61 win_sr=10% cum_sr=10%]
... [trial 1 | 1 sheep | 200,000 steps | ret(last 50)=-29.25 win_sr=12% cum_sr=11%]
... [trial 1 | 1 sheep | 300,000 steps | ret(last 50)=-31.55 win_sr=6% cum_sr=9%]
... [trial 1 | 1 sheep | 400,000 steps | ret(last 50)=-30.74 win_sr=10% cum_sr=9%]
... [trial 1 | 1 sheep | 500,000 steps | ret(last 50)=-32.89 win_sr=4% cum_sr=8%]
... [trial 1 | 1 sheep | 600,000 steps | ret(last 50)=-34.66 win_sr=4% cum_sr=7%]
... [trial 1 | 1 sheep | 700,000 steps | ret(last 50)=-31.44 win_sr=12% cum_sr=8%]
... [trial 1 | 1 sheep | 800,000 steps | ret(last 50)=-32.70 win_sr=6% cum_sr=8%]
... [trial 1 | 1 sheep | 900,000 steps | ret(last 50)=-35.48 win_sr=2% cum_sr=7%]
... [trial 1 | 1 sheep | 1,000,000 steps | ret(last 50)=-31.81 win_sr=10% cum_sr=8%]
... [trial 1 | 1 sheep | 1,100,000 steps | ret(last 50)=-28.53 win_sr=10% cum_sr=8%]
... [trial 1 | 1 sheep | 1,200,000 steps | ret(last 50)=-5.61 win_sr=62% cum_sr=13%]
... [trial 1 | 1 sheep | 1,300,000 steps | ret(last 50)=+11.97 win_sr=100% cum_sr=34%]
... [trial 1 | 1 sheep | 1,400,000 steps | ret(last 50)=+10.92 win_sr=96% cum_sr=50%]
... [trial 1 | 1 sheep | 1,500,000 steps | ret(last 50)=+11.97 win_sr=100% cum_sr=63%]
[Stage n_sheep=1] evaluating 30 eps
[Stage n_sheep=1] sr=100% mean_len=249 mean_min_pen=3.7m mean_act=0.41
[Stage n_sheep=2] training 1,500,000 steps
... [trial 1 | 2 sheep | 1,507,336 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 2 sheep | 1,607,336 steps | ret(last 47)=-1.11 win_sr=45% cum_sr=45%]
... [trial 1 | 2 sheep | 1,707,336 steps | ret(last 50)=-8.90 win_sr=8% cum_sr=27%]
... [trial 1 | 2 sheep | 1,807,336 steps | ret(last 50)=-5.28 win_sr=16% cum_sr=24%]
... [trial 1 | 2 sheep | 1,907,336 steps | ret(last 50)=+3.16 win_sr=58% cum_sr=33%]
... [trial 1 | 2 sheep | 2,007,336 steps | ret(last 50)=+10.26 win_sr=84% cum_sr=48%]
... [trial 1 | 2 sheep | 2,107,336 steps | ret(last 50)=+14.27 win_sr=100% cum_sr=64%]
... [trial 1 | 2 sheep | 2,207,336 steps | ret(last 50)=+14.08 win_sr=100% cum_sr=72%]
... [trial 1 | 2 sheep | 2,307,336 steps | ret(last 50)=+14.38 win_sr=100% cum_sr=77%]
... [trial 1 | 2 sheep | 2,407,336 steps | ret(last 50)=+14.27 win_sr=100% cum_sr=81%]
... [trial 1 | 2 sheep | 2,507,336 steps | ret(last 50)=+14.37 win_sr=100% cum_sr=84%]
... [trial 1 | 2 sheep | 2,607,336 steps | ret(last 50)=+14.33 win_sr=100% cum_sr=86%]
... [trial 1 | 2 sheep | 2,707,336 steps | ret(last 50)=+14.04 win_sr=100% cum_sr=87%]
... [trial 1 | 2 sheep | 2,807,336 steps | ret(last 50)=+14.25 win_sr=100% cum_sr=89%]
... [trial 1 | 2 sheep | 2,907,336 steps | ret(last 50)=+14.61 win_sr=100% cum_sr=90%]
... [trial 1 | 2 sheep | 3,007,336 steps | ret(last 50)=+13.98 win_sr=98% cum_sr=91%]
[Stage n_sheep=2] evaluating 30 eps
[Stage n_sheep=2] sr=100% mean_len=548 mean_min_pen=3.5m mean_act=0.92
[Stage n_sheep=3] training 1,500,000 steps
... [trial 1 | 3 sheep | 3,014,664 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 3 sheep | 3,114,664 steps | ret(last 50)=+16.10 win_sr=100% cum_sr=99%]
... [trial 1 | 3 sheep | 3,214,664 steps | ret(last 50)=+17.27 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,314,664 steps | ret(last 50)=+16.86 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,414,664 steps | ret(last 50)=+16.86 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,514,664 steps | ret(last 50)=+17.46 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,614,664 steps | ret(last 50)=+17.43 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,714,664 steps | ret(last 50)=+16.76 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,814,664 steps | ret(last 50)=+16.97 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 3,914,664 steps | ret(last 50)=+16.97 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,014,664 steps | ret(last 50)=+17.19 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,114,664 steps | ret(last 50)=+17.23 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,214,664 steps | ret(last 50)=+16.45 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,314,664 steps | ret(last 50)=+17.18 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,414,664 steps | ret(last 50)=+16.42 win_sr=100% cum_sr=100%]
... [trial 1 | 3 sheep | 4,514,664 steps | ret(last 50)=+16.32 win_sr=100% cum_sr=100%]
[Stage n_sheep=3] evaluating 30 eps
[Stage n_sheep=3] sr=100% mean_len=640 mean_min_pen=3.5m mean_act=1.06
[Stage n_sheep=4] training 1,500,000 steps
... [trial 1 | 4 sheep | 4,521,992 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 4 sheep | 4,621,992 steps | ret(last 50)=+18.61 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 4,721,992 steps | ret(last 50)=+18.82 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 4,821,992 steps | ret(last 50)=+18.91 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 4,921,992 steps | ret(last 50)=+18.55 win_sr=98% cum_sr=100%]
... [trial 1 | 4 sheep | 5,021,992 steps | ret(last 50)=+18.99 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,121,992 steps | ret(last 50)=+18.76 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,221,992 steps | ret(last 50)=+18.46 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,321,992 steps | ret(last 50)=+19.21 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,421,992 steps | ret(last 50)=+17.86 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,521,992 steps | ret(last 50)=+19.19 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,621,992 steps | ret(last 50)=+18.83 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,721,992 steps | ret(last 50)=+18.51 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,821,992 steps | ret(last 50)=+18.38 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 5,921,992 steps | ret(last 50)=+18.56 win_sr=100% cum_sr=100%]
... [trial 1 | 4 sheep | 6,021,992 steps | ret(last 50)=+18.82 win_sr=100% cum_sr=100%]
[Stage n_sheep=4] evaluating 30 eps
[Stage n_sheep=4] sr=100% mean_len=762 mean_min_pen=3.5m mean_act=1.26
[Stage n_sheep=5] training 1,500,000 steps
... [trial 1 | 5 sheep | 6,029,320 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 5 sheep | 6,129,320 steps | ret(last 50)=+20.46 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,229,320 steps | ret(last 50)=+20.41 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,329,320 steps | ret(last 50)=+20.58 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,429,320 steps | ret(last 50)=+21.10 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,529,320 steps | ret(last 50)=+20.48 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,629,320 steps | ret(last 50)=+20.56 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,729,320 steps | ret(last 50)=+20.51 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,829,320 steps | ret(last 50)=+20.70 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 6,929,320 steps | ret(last 50)=+20.83 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,029,320 steps | ret(last 50)=+21.52 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,129,320 steps | ret(last 50)=+21.62 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,229,320 steps | ret(last 50)=+21.22 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,329,320 steps | ret(last 50)=+21.17 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,429,320 steps | ret(last 50)=+21.00 win_sr=100% cum_sr=100%]
... [trial 1 | 5 sheep | 7,529,320 steps | ret(last 50)=+20.48 win_sr=100% cum_sr=100%]
[Stage n_sheep=5] evaluating 30 eps
[Stage n_sheep=5] sr=100% mean_len=931 mean_min_pen=3.6m mean_act=1.31
[Stage n_sheep=6] training 1,500,000 steps
... [trial 1 | 6 sheep | 7,536,648 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 6 sheep | 7,636,648 steps | ret(last 50)=+21.89 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 7,736,648 steps | ret(last 50)=+22.98 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 7,836,648 steps | ret(last 50)=+22.66 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 7,936,648 steps | ret(last 50)=+23.23 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,036,648 steps | ret(last 50)=+22.83 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,136,648 steps | ret(last 50)=+22.65 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,236,648 steps | ret(last 50)=+22.22 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,336,648 steps | ret(last 50)=+22.45 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,436,648 steps | ret(last 50)=+22.55 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,536,648 steps | ret(last 50)=+22.99 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,636,648 steps | ret(last 50)=+21.99 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,736,648 steps | ret(last 50)=+22.30 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,836,648 steps | ret(last 50)=+23.06 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 8,936,648 steps | ret(last 50)=+23.32 win_sr=100% cum_sr=100%]
... [trial 1 | 6 sheep | 9,036,648 steps | ret(last 50)=+21.80 win_sr=100% cum_sr=100%]
[Stage n_sheep=6] evaluating 30 eps
[Stage n_sheep=6] sr=100% mean_len=1082 mean_min_pen=3.6m mean_act=1.35
[Stage n_sheep=7] training 1,500,000 steps
... [trial 1 | 7 sheep | 9,043,976 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 7 sheep | 9,143,976 steps | ret(last 50)=+25.57 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,243,976 steps | ret(last 50)=+24.76 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,343,976 steps | ret(last 50)=+24.69 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,443,976 steps | ret(last 50)=+26.12 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,543,976 steps | ret(last 50)=+25.53 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,643,976 steps | ret(last 50)=+25.39 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,743,976 steps | ret(last 50)=+24.45 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,843,976 steps | ret(last 50)=+26.45 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 9,943,976 steps | ret(last 50)=+24.51 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,043,976 steps | ret(last 50)=+24.80 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,143,976 steps | ret(last 50)=+25.56 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,243,976 steps | ret(last 50)=+25.75 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,343,976 steps | ret(last 50)=+25.64 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,443,976 steps | ret(last 50)=+26.45 win_sr=100% cum_sr=100%]
... [trial 1 | 7 sheep | 10,543,976 steps | ret(last 50)=+25.19 win_sr=100% cum_sr=100%]
[Stage n_sheep=7] evaluating 30 eps
[Stage n_sheep=7] sr=100% mean_len=1081 mean_min_pen=3.5m mean_act=1.37
[Stage n_sheep=8] training 1,500,000 steps
... [trial 1 | 8 sheep | 10,551,304 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 8 sheep | 10,651,304 steps | ret(last 50)=+26.63 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 10,751,304 steps | ret(last 50)=+27.63 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 10,851,304 steps | ret(last 50)=+27.53 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 10,951,304 steps | ret(last 50)=+27.43 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,051,304 steps | ret(last 50)=+27.70 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,151,304 steps | ret(last 50)=+26.53 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,251,304 steps | ret(last 50)=+27.24 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,351,304 steps | ret(last 50)=+27.14 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,451,304 steps | ret(last 50)=+27.43 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,551,304 steps | ret(last 50)=+27.25 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,651,304 steps | ret(last 50)=+27.40 win_sr=98% cum_sr=100%]
... [trial 1 | 8 sheep | 11,751,304 steps | ret(last 50)=+27.35 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,851,304 steps | ret(last 50)=+26.33 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 11,951,304 steps | ret(last 50)=+26.89 win_sr=100% cum_sr=100%]
... [trial 1 | 8 sheep | 12,051,304 steps | ret(last 50)=+27.86 win_sr=100% cum_sr=100%]
[Stage n_sheep=8] evaluating 30 eps
[Stage n_sheep=8] sr=100% mean_len=1311 mean_min_pen=3.5m mean_act=1.38
[Stage n_sheep=9] training 1,500,000 steps
... [trial 1 | 9 sheep | 12,058,632 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 9 sheep | 12,158,632 steps | ret(last 50)=+29.62 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,258,632 steps | ret(last 50)=+31.32 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,358,632 steps | ret(last 50)=+30.30 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,458,632 steps | ret(last 50)=+29.33 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,558,632 steps | ret(last 50)=+28.83 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,658,632 steps | ret(last 50)=+29.02 win_sr=98% cum_sr=100%]
... [trial 1 | 9 sheep | 12,758,632 steps | ret(last 50)=+29.60 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,858,632 steps | ret(last 50)=+29.88 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 12,958,632 steps | ret(last 50)=+30.12 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 13,058,632 steps | ret(last 50)=+28.80 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 13,158,632 steps | ret(last 50)=+30.33 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 13,258,632 steps | ret(last 50)=+27.85 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 13,358,632 steps | ret(last 50)=+28.21 win_sr=96% cum_sr=100%]
... [trial 1 | 9 sheep | 13,458,632 steps | ret(last 50)=+29.88 win_sr=100% cum_sr=100%]
... [trial 1 | 9 sheep | 13,558,632 steps | ret(last 50)=+29.06 win_sr=98% cum_sr=100%]
[Stage n_sheep=9] evaluating 30 eps
[Stage n_sheep=9] sr=100% mean_len=1435 mean_min_pen=3.6m mean_act=1.39
[Stage n_sheep=10] training 1,500,000 steps
... [trial 1 | 10 sheep | 13,565,960 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | 10 sheep | 13,665,960 steps | ret(last 50)=+30.42 win_sr=96% cum_sr=96%]
... [trial 1 | 10 sheep | 13,765,960 steps | ret(last 50)=+29.97 win_sr=92% cum_sr=95%]
... [trial 1 | 10 sheep | 13,865,960 steps | ret(last 50)=+30.45 win_sr=82% cum_sr=90%]
... [trial 1 | 10 sheep | 13,965,960 steps | ret(last 50)=+29.82 win_sr=90% cum_sr=91%]
... [trial 1 | 10 sheep | 14,065,960 steps | ret(last 50)=+29.66 win_sr=90% cum_sr=91%]
... [trial 1 | 10 sheep | 14,165,960 steps | ret(last 50)=+31.57 win_sr=98% cum_sr=92%]
... [trial 1 | 10 sheep | 14,265,960 steps | ret(last 50)=+31.71 win_sr=96% cum_sr=93%]
... [trial 1 | 10 sheep | 14,365,960 steps | ret(last 50)=+31.75 win_sr=94% cum_sr=93%]
... [trial 1 | 10 sheep | 14,465,960 steps | ret(last 50)=+29.46 win_sr=88% cum_sr=93%]
... [trial 1 | 10 sheep | 14,565,960 steps | ret(last 50)=+29.62 win_sr=94% cum_sr=93%]
... [trial 1 | 10 sheep | 14,665,960 steps | ret(last 50)=+31.64 win_sr=98% cum_sr=93%]
... [trial 1 | 10 sheep | 14,765,960 steps | ret(last 50)=+30.86 win_sr=90% cum_sr=93%]
... [trial 1 | 10 sheep | 14,865,960 steps | ret(last 50)=+31.65 win_sr=90% cum_sr=93%]
... [trial 1 | 10 sheep | 14,965,960 steps | ret(last 50)=+31.75 win_sr=92% cum_sr=93%]
... [trial 1 | 10 sheep | 15,065,960 steps | ret(last 50)=+30.24 win_sr=100% cum_sr=93%]
[Stage n_sheep=10] evaluating 30 eps
[Stage n_sheep=10] sr=90% mean_len=1841 mean_min_pen=3.6m mean_act=1.39
[Consolidation] mixed n_sheep ∈ [1, 10], 2,000,000 steps
... [trial 1 | consolidate | 15,073,288 steps | ret(last 0)=+nan win_sr=nan% cum_sr=nan%]
... [trial 1 | consolidate | 15,173,288 steps | ret(last 50)=+20.69 win_sr=94% cum_sr=95%]
... [trial 1 | consolidate | 15,273,288 steps | ret(last 50)=+20.62 win_sr=90% cum_sr=92%]
... [trial 1 | consolidate | 15,373,288 steps | ret(last 50)=+20.25 win_sr=94% cum_sr=93%]
... [trial 1 | consolidate | 15,473,288 steps | ret(last 50)=+19.82 win_sr=96% cum_sr=94%]
... [trial 1 | consolidate | 15,573,288 steps | ret(last 50)=+20.56 win_sr=94% cum_sr=94%]
... [trial 1 | consolidate | 15,673,288 steps | ret(last 50)=+20.56 win_sr=92% cum_sr=94%]
... [trial 1 | consolidate | 15,773,288 steps | ret(last 50)=+19.43 win_sr=94% cum_sr=95%]
... [trial 1 | consolidate | 15,873,288 steps | ret(last 50)=+21.85 win_sr=98% cum_sr=95%]
... [trial 1 | consolidate | 15,973,288 steps | ret(last 50)=+21.84 win_sr=94% cum_sr=95%]
... [trial 1 | consolidate | 16,073,288 steps | ret(last 50)=+22.13 win_sr=98% cum_sr=95%]
... [trial 1 | consolidate | 16,173,288 steps | ret(last 50)=+21.89 win_sr=94% cum_sr=95%]
... [trial 1 | consolidate | 16,273,288 steps | ret(last 50)=+21.88 win_sr=98% cum_sr=95%]
... [trial 1 | consolidate | 16,373,288 steps | ret(last 50)=+20.81 win_sr=94% cum_sr=95%]
... [trial 1 | consolidate | 16,473,288 steps | ret(last 50)=+20.91 win_sr=98% cum_sr=95%]
... [trial 1 | consolidate | 16,573,288 steps | ret(last 50)=+21.13 win_sr=98% cum_sr=95%]
... [trial 1 | consolidate | 16,673,288 steps | ret(last 50)=+19.85 win_sr=100% cum_sr=95%]
... [trial 1 | consolidate | 16,773,288 steps | ret(last 50)=+22.30 win_sr=92% cum_sr=95%]
... [trial 1 | consolidate | 16,873,288 steps | ret(last 50)=+20.61 win_sr=96% cum_sr=95%]
... [trial 1 | consolidate | 16,973,288 steps | ret(last 50)=+21.93 win_sr=98% cum_sr=96%]
... [trial 1 | consolidate | 17,073,288 steps | ret(last 50)=+21.86 win_sr=98% cum_sr=96%]
[Consolidation] re-evaluating all sheep counts
[Consolidation] n_sheep=1 sr=97% mean_len=377 mean_min_pen=3.5m mean_act=1.39
[Consolidation] n_sheep=2 sr=47% mean_len=1718 mean_min_pen=2.4m mean_act=1.39
[Consolidation] n_sheep=3 sr=93% mean_len=970 mean_min_pen=3.2m mean_act=1.39
[Consolidation] n_sheep=4 sr=97% mean_len=1008 mean_min_pen=3.3m mean_act=1.39
[Consolidation] n_sheep=5 sr=100% mean_len=1176 mean_min_pen=3.3m mean_act=1.39
[Consolidation] n_sheep=6 sr=100% mean_len=1305 mean_min_pen=3.3m mean_act=1.39
[Consolidation] n_sheep=7 sr=100% mean_len=1300 mean_min_pen=3.4m mean_act=1.39
[Consolidation] n_sheep=8 sr=100% mean_len=1461 mean_min_pen=3.5m mean_act=1.39
[Consolidation] n_sheep=9 sr=87% mean_len=1607 mean_min_pen=3.8m mean_act=1.39
[Consolidation] n_sheep=10 sr=80% mean_len=1801 mean_min_pen=3.7m mean_act=1.39
============================================================
REPLAY SUMMARY
============================================================
n_sheep=1 sr= 97% len= 377 min_pen= 3.5m act=1.39
n_sheep=2 sr= 47% len= 1718 min_pen= 2.4m act=1.39
n_sheep=3 sr= 93% len= 970 min_pen= 3.2m act=1.39
n_sheep=4 sr= 97% len= 1008 min_pen= 3.3m act=1.39
n_sheep=5 sr=100% len= 1176 min_pen= 3.3m act=1.39
n_sheep=6 sr=100% len= 1305 min_pen= 3.3m act=1.39
n_sheep=7 sr=100% len= 1300 min_pen= 3.4m act=1.39
n_sheep=8 sr=100% len= 1461 min_pen= 3.5m act=1.39
n_sheep=9 sr= 87% len= 1607 min_pen= 3.8m act=1.39
n_sheep=10 sr= 80% len= 1801 min_pen= 3.7m act=1.39
Total time: 110.1 min
Artefacts: runs/final_v3/
training/runs/final_v3/config.json
+11
View File
@@ -0,0 +1,11 @@
{
"W_PER_SHEEP": 1.0,
"W_ALIGN": 0.0,
"W_PEN_BONUS": 5.0,
"W_STEP_COST": 0.02,
"W_COMPLETE": 200.0,
"W_COMPACT": 1.5,
"ALIGN_SHAPE": "standoff",
"ALIGN_GATED": false,
"ent_coef": 0.02
}
training/runs/final_v3/final_model.zip
BIN
View File
Binary file not shown.
training/runs/final_v3/stage_results.json
+72
View File
@@ -0,0 +1,72 @@
[
{
"n_sheep": 1,
"sr": 0.9666666666666667,
"mean_len": 377.3666666666667,
"mean_min_pen": 3.5389957586924234,
"mean_act": 1.3908841227086732
},
{
"n_sheep": 2,
"sr": 0.4666666666666667,
"mean_len": 1717.6333333333334,
"mean_min_pen": 2.4164488633473713,
"mean_act": 1.3922284740020803
},
{
"n_sheep": 3,
"sr": 0.9333333333333333,
"mean_len": 970.2666666666667,
"mean_min_pen": 3.203955141703288,
"mean_act": 1.3945290882248416
},
{
"n_sheep": 4,
"sr": 0.9666666666666667,
"mean_len": 1008.0,
"mean_min_pen": 3.279213563601176,
"mean_act": 1.3918021049325862
},
{
"n_sheep": 5,
"sr": 1.0,
"mean_len": 1175.8666666666666,
"mean_min_pen": 3.3209743976593016,
"mean_act": 1.3925684957666513
},
{
"n_sheep": 6,
"sr": 1.0,
"mean_len": 1305.0,
"mean_min_pen": 3.312229561805725,
"mean_act": 1.391130207932886
},
{
"n_sheep": 7,
"sr": 1.0,
"mean_len": 1300.0,
"mean_min_pen": 3.363971138000488,
"mean_act": 1.392986050516367
},
{
"n_sheep": 8,
"sr": 1.0,
"mean_len": 1461.3666666666666,
"mean_min_pen": 3.4741388003031415,
"mean_act": 1.392040583461347
},
{
"n_sheep": 9,
"sr": 0.8666666666666667,
"mean_len": 1606.7333333333333,
"mean_min_pen": 3.835897175470988,
"mean_act": 1.3907199496534952
},
{
"n_sheep": 10,
"sr": 0.8,
"mean_len": 1800.9666666666667,
"mean_min_pen": 3.741190282503764,
"mean_act": 1.392501896076031
}
]
training/runs/final_v3/vecnorm.pkl
BIN
View File
Binary file not shown.