cartpole-swingup: the draft controller against the accepted one
Scenario s1: pole hanging at 180 degrees, half-length 0.5 m, cart mass 1.0 kg, force clamped to 20 N. Both runs come from the built plimsoll/sandbox-sim image through the project API; the fingerprints below are the SHA-256 of each trajectory as recorded from that image.
The simulator is written in C, compiled to WebAssembly and shipped in that image: its source, EXTERNAL · source repo ↗. A controller is a separate program that reads the simulator's observations each tick and sets its input. This page runs two hand-written controllers against it: a draft that makes a plausible mistake and fails, and an accepted one that passes the environment's scoring program. Published: the accepted controller's law (the same fingerprints), EXTERNAL · source repo ↗; its C port, EXTERNAL · source repo ↗; and all four scenarios with their fingerprints, EXTERNAL · source repo ↗. The draft controller and the scoring program are not published. Every simulator in the image, EXTERNAL · source repo ↗.
Work in progress. These charts show two hand-written reference controllers. No AI-generated controller is plotted for this environment yet.
Draft controlleroff trackt up none, off track at 0.51, max abs x 3632.603
Accepted controllerscore 0.879t up 2.41, off track at none, max abs x 2.085
Draft controllerAccepted controllerhard limit
Table view (100 rows)
| seconds | draft x_m | draft v_m_per_s | draft theta_rad_from_upright_unwrapped | draft omega_rad_per_s | draft action | accepted x_m | accepted v_m_per_s | accepted theta_rad_from_upright_unwrapped | accepted omega_rad_per_s | accepted action |
|---|---|---|---|---|---|---|---|---|---|---|
| 0 | 0.0000 | 0.0000 | 3.1416 | 0.0000 | 125.6636 | 0.0000 | 0.0000 | 3.1416 | 0.0000 | -20.0000 |
| 0.2 | 0.3854 | 3.8328 | 3.6870 | 5.0464 | 176.9315 | -0.3854 | -3.8313 | 2.5962 | -5.0445 | -16.8785 |
| 0.4 | 1.4965 | 7.2575 | 4.7843 | 4.8198 | 224.2248 | -1.2911 | -4.8261 | 1.6566 | -3.5623 | -2.2012 |
| 0.6 | 3.3054 | 10.9100 | 5.3031 | -0.0365 | 226.1572 | -1.9992 | -1.7461 | 1.1691 | -1.7428 | 20.0000 |
| 0.8 | 5.8567 | 14.5599 | 4.7751 | -4.8836 | 187.0029 | -2.0284 | 1.0681 | 0.8456 | -1.4451 | 8.6742 |
| 1 | 9.1053 | 17.9832 | 3.6691 | -5.0631 | 148.5352 | -1.7023 | 2.0148 | 0.6382 | -0.5318 | 2.8706 |
| 1.2 | 13.0798 | 21.8206 | 3.1225 | 0.0527 | 160.0652 | -1.3191 | 1.3914 | 0.7273 | 1.9642 | -5.1247 |
| 1.4 | 17.8296 | 25.6552 | 3.6837 | 5.1447 | 216.5548 | -1.1045 | 0.9068 | 1.4106 | 4.8610 | -1.6167 |
| 1.6 | 23.3044 | 29.0724 | 4.7983 | 4.8808 | 268.7109 | -0.9051 | 1.0887 | 2.6672 | 7.4804 | -1.8027 |
| 1.8 | 29.4764 | 32.7284 | 5.3224 | -0.0436 | 274.8807 | -0.7037 | 0.9178 | 4.1346 | 6.5296 | 1.5227 |
| 2 | 36.3919 | 36.3809 | 4.7866 | -4.9533 | 239.4721 | -0.5456 | 0.5023 | 5.1648 | 3.8270 | -2.3350 |
| 2.2 | 44.0040 | 39.7971 | 3.6630 | -5.1543 | 204.5511 | -0.4741 | 0.2829 | 5.7276 | 1.9327 | -0.5918 |
| 2.4 | 52.3414 | 43.6369 | 3.1031 | 0.0131 | 220.1675 | -0.4770 | -0.4002 | 6.0715 | 1.7827 | -0.4329 |
| 2.6 | 61.4550 | 47.4776 | 3.6639 | 5.1931 | 281.4545 | -0.5130 | 0.2199 | 6.3308 | 0.6685 | 4.9548 |
| 2.8 | 71.2942 | 50.8905 | 4.7967 | 4.9958 | 339.0327 | -0.3838 | 0.9890 | 6.3582 | -0.2559 | 2.3257 |
| 3 | 81.8293 | 54.5444 | 5.3419 | 0.0405 | 350.2525 | -0.1622 | 1.1308 | 6.2870 | -0.3477 | -0.6172 |
| 3.2 | 93.1088 | 58.2054 | 4.8144 | -4.9684 | 319.0498 | 0.0453 | 0.9226 | 6.2410 | -0.1040 | -1.2392 |
| 3.4 | 105.0851 | 61.6110 | 3.6740 | -5.2988 | 287.1632 | 0.2092 | 0.7347 | 6.2377 | 0.0415 | -0.6692 |
| 3.6 | 117.7849 | 65.4488 | 3.0837 | -0.1255 | 305.9522 | 0.3470 | 0.6571 | 6.2473 | 0.0382 | -0.2416 |
| 3.8 | 131.2614 | 69.2996 | 3.6266 | 5.1838 | 371.5436 | 0.4747 | 0.6201 | 6.2504 | -0.0051 | -0.2403 |
| 4 | 145.4658 | 72.7125 | 4.7779 | 5.1666 | 435.1271 | 0.5937 | 0.5642 | 6.2472 | -0.0217 | -0.3898 |
| 4.2 | 160.3641 | 76.3575 | 5.3609 | 0.2229 | 452.2730 | 0.6988 | 0.4842 | 6.2435 | -0.0135 | -0.4736 |
| 4.4 | 176.0074 | 80.0333 | 4.8593 | -4.9200 | 425.8147 | 0.7870 | 0.3967 | 6.2420 | -0.0020 | -0.4744 |
| 4.6 | 192.3488 | 83.4254 | 3.7042 | -5.4951 | 396.4683 | 0.8578 | 0.3122 | 6.2422 | 0.0035 | -0.4507 |
| 4.8 | 209.4102 | 87.2559 | 3.0657 | -0.3701 | 417.4416 | 0.9122 | 0.2317 | 6.2431 | 0.0049 | -0.4354 |
| 5 | 227.2489 | 91.1202 | 3.5711 | 5.1031 | 486.7286 | 0.9507 | 0.1533 | 6.2442 | 0.0060 | -0.4267 |
| 5.2 | 245.8193 | 94.5395 | 4.7393 | 5.3905 | 556.8821 | 0.9737 | 0.0766 | 6.2456 | 0.0081 | -0.4140 |
| 5.4 | 265.0807 | 98.1675 | 5.3775 | 0.5104 | 580.8992 | 0.9816 | 0.0029 | 6.2474 | 0.0105 | -0.3933 |
| 5.6 | 285.0876 | 101.8639 | 4.9215 | -4.7941 | 559.8403 | 0.9752 | -0.0665 | 6.2497 | 0.0125 | -0.3664 |
| 5.8 | 305.7951 | 105.2420 | 3.7565 | -5.7343 | 532.6237 | 0.9554 | -0.1306 | 6.2524 | 0.0141 | -0.3360 |
| 6 | 327.2175 | 109.0579 | 3.0517 | -0.7273 | 554.7087 | 0.9234 | -0.1889 | 6.2553 | 0.0152 | -0.3033 |
| 6.2 | 349.4175 | 112.9375 | 3.4977 | 4.9311 | 626.9194 | 0.8803 | -0.2412 | 6.2585 | 0.0161 | -0.2686 |
| 6.4 | 372.3546 | 116.3732 | 4.6777 | 5.6587 | 704.1298 | 0.8274 | -0.2869 | 6.2618 | 0.0168 | -0.2321 |
| 6.6 | 395.9793 | 119.9741 | 5.3883 | 0.9095 | 736.0340 | 0.7661 | -0.3259 | 6.2652 | 0.0172 | -0.1944 |
| 6.8 | 420.3492 | 123.6957 | 5.0000 | -4.5727 | 721.1823 | 0.6976 | -0.3579 | 6.2686 | 0.0173 | -0.1562 |
| 7 | 445.4240 | 127.0633 | 3.8340 | -5.9986 | 695.8537 | 0.6234 | -0.3830 | 6.2721 | 0.0172 | -0.1182 |
| 7.2 | 471.2071 | 130.8546 | 3.0460 | -1.2030 | 717.8874 | 0.5449 | -0.4013 | 6.2755 | 0.0168 | -0.0807 |
| 7.4 | 497.7670 | 134.7492 | 3.4080 | 4.6434 | 792.0520 | 0.4633 | -0.4128 | 6.2788 | 0.0162 | -0.0444 |
| 7.6 | 525.0713 | 138.2157 | 4.5896 | 5.9542 | 876.6402 | 0.3802 | -0.4178 | 6.2820 | 0.0155 | -0.0096 |
| 7.8 | 553.0600 | 141.7776 | 5.3888 | 1.4249 | 917.5136 | 0.2967 | -0.4166 | 6.2850 | 0.0145 | 0.0233 |
| 8 | 581.7922 | 145.5263 | 5.0928 | -4.2341 | 909.8585 | 0.2139 | -0.4096 | 6.2877 | 0.0134 | 0.0538 |
| 8.2 | 611.2356 | 148.8930 | 3.9403 | -6.2583 | 886.4493 | 0.1332 | -0.3973 | 6.2903 | 0.0122 | 0.0818 |
| 8.4 | 641.3791 | 152.6456 | 3.0542 | -1.8015 | 907.1847 | 0.0553 | -0.3802 | 6.2926 | 0.0109 | 0.1070 |
| 8.6 | 672.2977 | 156.5526 | 3.3052 | 4.2133 | 982.1239 | -0.0186 | -0.3587 | 6.2947 | 0.0095 | 0.1291 |
| 8.8 | 703.9692 | 160.0687 | 4.4710 | 6.2485 | 1074.1187 | -0.0879 | -0.3335 | 6.2964 | 0.0081 | 0.1482 |
| 9 | 736.3230 | 163.5790 | 5.3725 | 2.0583 | 1125.0935 | -0.1518 | -0.3050 | 6.2979 | 0.0066 | 0.1640 |
| 9.2 | 769.4164 | 167.3522 | 5.1956 | -3.7547 | 1125.8204 | -0.2098 | -0.2740 | 6.2991 | 0.0051 | 0.1765 |
| 9.4 | 803.2294 | 170.7356 | 4.0784 | -6.4701 | 1104.7511 | -0.2614 | -0.2410 | 6.2999 | 0.0037 | 0.1858 |
| 9.6 | 837.7339 | 174.4308 | 3.0838 | -2.5239 | 1122.8964 | -0.3062 | -0.2066 | 6.3005 | 0.0022 | 0.1920 |
| 9.8 | 873.0098 | 178.3459 | 3.1950 | 3.6170 | 1197.2403 | -0.3440 | -0.1713 | 6.3008 | 0.0009 | 0.1951 |
| 10 | 909.0477 | 181.9324 | 4.3185 | 6.4978 | 1296.2087 | -0.3747 | -0.1357 | 6.3009 | -0.0004 | 0.1952 |
| 10.2 | 945.7685 | 185.3806 | 5.3313 | 2.8060 | 1358.4323 | -0.3983 | -0.1004 | 6.3007 | -0.0016 | 0.1926 |
| 10.4 | 983.2219 | 189.1697 | 5.3022 | -3.1123 | 1368.9179 | -0.4149 | -0.0657 | 6.3002 | -0.0028 | 0.1875 |
| 10.6 | 1021.4051 | 192.5947 | 4.2499 | -6.5777 | 1351.1067 | -0.4247 | -0.0322 | 6.2996 | -0.0038 | 0.1800 |
| 10.8 | 1060.2719 | 196.2106 | 3.1442 | -3.3643 | 1365.4298 | -0.4279 | -0.0002 | 6.2987 | -0.0047 | 0.1704 |
| 11 | 1099.9038 | 200.1287 | 3.0859 | 2.8383 | 1437.6591 | -0.4249 | 0.0299 | 6.2977 | -0.0055 | 0.1590 |
| 11.2 | 1140.3062 | 203.8030 | 4.1304 | 6.6370 | 1542.5089 | -0.4162 | 0.0577 | 6.2966 | -0.0061 | 0.1461 |
| 11.4 | 1181.3965 | 207.1871 | 5.2555 | 3.6539 | 1617.0731 | -0.4020 | 0.0831 | 6.2953 | -0.0066 | 0.1318 |
| 11.6 | 1223.2090 | 210.9754 | 5.4031 | -2.2895 | 1638.8616 | -0.3831 | 0.1058 | 6.2939 | -0.0070 | 0.1166 |
| 11.8 | 1265.7618 | 214.4705 | 4.4536 | -6.5162 | 1625.7962 | -0.3599 | 0.1256 | 6.2925 | -0.0073 | 0.1007 |
| 12 | 1308.9937 | 217.9874 | 3.2466 | -4.3010 | 1635.3405 | -0.3331 | 0.1425 | 6.2910 | -0.0075 | 0.0842 |
| 12.2 | 1352.9802 | 221.9022 | 2.9893 | 1.8721 | 1703.8145 | -0.3032 | 0.1564 | 6.2895 | -0.0075 | 0.0676 |
| 12.4 | 1397.7441 | 225.6705 | 3.9081 | 6.5766 | 1812.6226 | -0.2708 | 0.1672 | 6.2880 | -0.0075 | 0.0510 |
| 12.6 | 1443.2071 | 229.0062 | 5.1339 | 4.5712 | 1900.4255 | -0.2365 | 0.1751 | 6.2865 | -0.0073 | 0.0347 |
| 12.8 | 1489.3782 | 232.7678 | 5.4859 | -1.2779 | 1935.1931 | -0.2009 | 0.1800 | 6.2851 | -0.0071 | 0.0189 |
| 13 | 1536.2985 | 236.3565 | 4.6844 | -6.2183 | 1928.9394 | -0.1647 | 0.1821 | 6.2837 | -0.0067 | 0.0037 |
| 13.2 | 1583.8996 | 239.7682 | 3.4029 | -5.2800 | 1933.3846 | -0.1282 | 0.1815 | 6.2824 | -0.0063 | -0.0106 |
| 13.4 | 1632.2397 | 243.6683 | 2.9197 | 0.7220 | 1996.3068 | -0.0922 | 0.1784 | 6.2812 | -0.0058 | -0.0238 |
| 13.6 | 1681.3613 | 247.5183 | 3.6591 | 6.2085 | 2106.2876 | -0.0570 | 0.1730 | 6.2800 | -0.0053 | -0.0360 |
| 13.8 | 1731.1996 | 250.8495 | 4.9553 | 5.4994 | 2207.7582 | -0.0231 | 0.1655 | 6.2790 | -0.0047 | -0.0469 |
| 14 | 1781.7301 | 254.5480 | 5.5348 | -0.0790 | 2257.2740 | 0.0090 | 0.1561 | 6.2782 | -0.0041 | -0.0566 |
| 14.2 | 1833.0145 | 258.2379 | 4.9314 | -5.6215 | 2260.4021 | 0.0392 | 0.1450 | 6.2774 | -0.0035 | -0.0648 |
| 14.4 | 1884.9897 | 261.5691 | 3.6237 | -6.1913 | 2260.5486 | 0.0670 | 0.1326 | 6.2768 | -0.0029 | -0.0716 |
| 14.6 | 1937.6830 | 265.4278 | 2.8947 | -0.6054 | 2315.8730 | 0.0922 | 0.1190 | 6.2763 | -0.0022 | -0.0771 |
| 14.8 | 1991.1584 | 269.3300 | 3.3991 | 5.4381 | 2423.6414 | 0.1145 | 0.1046 | 6.2759 | -0.0016 | -0.0811 |
| 15 | 2045.3725 | 272.7287 | 4.7103 | 6.3419 | 2538.2242 | 0.1340 | 0.0896 | 6.2756 | -0.0010 | -0.0837 |
| 15.2 | 2100.2656 | 276.3206 | 5.5307 | 1.2944 | 2604.2883 | 0.1504 | 0.0742 | 6.2755 | -0.0004 | -0.0850 |
| 15.4 | 2155.9097 | 280.0956 | 5.1772 | -4.6780 | 2619.7023 | 0.1637 | 0.0587 | 6.2755 | 0.0002 | -0.0851 |
| 15.6 | 2212.2629 | 283.4136 | 3.9135 | -6.8594 | 2617.9197 | 0.1739 | 0.0433 | 6.2756 | 0.0007 | -0.0839 |
| 15.8 | 2269.3110 | 287.1791 | 2.9350 | -2.1021 | 2663.3799 | 0.1810 | 0.0282 | 6.2758 | 0.0012 | -0.0816 |
| 16 | 2327.1372 | 291.1016 | 3.1525 | 4.2379 | 2765.5280 | 0.1852 | 0.0136 | 6.2760 | 0.0017 | -0.0783 |
| 16.2 | 2385.7237 | 294.6449 | 4.3953 | 6.9507 | 2890.9322 | 0.1865 | -0.0003 | 6.2764 | 0.0020 | -0.0742 |
| 16.4 | 2444.9852 | 298.0957 | 5.4522 | 2.8125 | 2975.2302 | 0.1852 | -0.0134 | 6.2769 | 0.0024 | -0.0692 |
| 16.6 | 2504.9850 | 301.9152 | 5.3969 | -3.3719 | 3005.9160 | 0.1813 | -0.0255 | 6.2774 | 0.0027 | -0.0635 |
| 16.8 | 2565.7165 | 305.3163 | 4.2657 | -7.0846 | 3006.2382 | 0.1751 | -0.0365 | 6.2779 | 0.0029 | -0.0573 |
| 17 | 2627.1249 | 308.9212 | 3.0642 | -3.7412 | 3039.9099 | 0.1668 | -0.0464 | 6.2785 | 0.0031 | -0.0506 |
| 17.2 | 2689.2998 | 312.8462 | 2.9504 | 2.6680 | 3133.5036 | 0.1566 | -0.0550 | 6.2792 | 0.0032 | -0.0437 |
| 17.4 | 2752.2507 | 316.5712 | 4.0178 | 7.1089 | 3265.0762 | 0.1449 | -0.0623 | 6.2798 | 0.0033 | -0.0365 |
| 17.6 | 2815.8890 | 319.8933 | 5.2762 | 4.4031 | 3368.8471 | 0.1318 | -0.0683 | 6.2805 | 0.0033 | -0.0293 |
| 17.8 | 2880.2425 | 323.6953 | 5.5596 | -1.7328 | 3417.6597 | 0.1176 | -0.0730 | 6.2811 | 0.0033 | -0.0220 |
| 18 | 2945.3471 | 327.2571 | 4.6582 | -6.7173 | 3425.3449 | 0.1027 | -0.0764 | 6.2818 | 0.0032 | -0.0149 |
| 18.2 | 3011.1258 | 330.6665 | 3.3066 | -5.4110 | 3447.0007 | 0.0871 | -0.0785 | 6.2824 | 0.0031 | -0.0080 |
| 18.4 | 3077.6479 | 334.5809 | 2.8265 | 0.8224 | 3529.4016 | 0.0713 | -0.0794 | 6.2830 | 0.0029 | -0.0014 |
| 18.6 | 3144.9532 | 338.4482 | 3.6056 | 6.5461 | 3660.3549 | 0.0555 | -0.0791 | 6.2836 | 0.0027 | 0.0048 |
| 18.8 | 3212.9752 | 341.7469 | 4.9835 | 5.9092 | 3783.6079 | 0.0398 | -0.0777 | 6.2841 | 0.0025 | 0.0106 |
| 19 | 3281.6845 | 345.4480 | 5.6305 | 0.1788 | 3853.2467 | 0.0244 | -0.0753 | 6.2846 | 0.0023 | 0.0158 |
| 19.2 | 3351.1525 | 349.1778 | 5.0531 | -5.6846 | 3874.0299 | 0.0097 | -0.0720 | 6.2850 | 0.0021 | 0.0206 |
| 19.4 | 3421.3132 | 352.4618 | 3.6768 | -6.8006 | 3886.8452 | -0.0043 | -0.0679 | 6.2854 | 0.0018 | 0.0248 |
| 19.6 | 3492.1828 | 356.3100 | 2.8158 | -1.2412 | 3954.9203 | -0.0174 | -0.0631 | 6.2857 | 0.0015 | 0.0283 |
| 19.8 | 3563.8350 | 360.2320 | 3.2119 | 5.1179 | 4078.1316 | -0.0295 | -0.0576 | 6.2860 | 0.0012 | 0.0313 |
Fingerprints, scenario s1 (3.14159, 0.5, 1)
draft: 1fff6ac98cb75a2b220b2e781d08c098a30d8508c1e3f084bf1cd96d855dc341
accepted: d536a067c8cb2ec987d031fab4561d06c8453aa39a1cda2f60b91bcb0d198829