Test26_1200

training/runs/v1/config.json

@@ -0,0 +1,14 @@
+{
+  "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
+}

training/runs/v1/stage_results.json

@@ -0,0 +1,218 @@
+[
+  {
+    "sr": 1.0,
+    "mean_len": 243.0,
+    "mean_min_pen": 3.7120999256769815,
+    "mean_act": 0.3930775734995823,
+    "failure_modes": {
+      "SUCCESS": 30
+    },
+    "reward_per_step": {
+      "progress": 0.11411363949746262,
+      "alignment": 0.00034729298515464674,
+      "compact": 0.0,
+      "wall_touch": 0.0,
+      "pen_bonus": 0.0411522633744856,
+      "step_cost": -0.020000000000000108,
+      "complete": 0.411522633744856
+    },
+    "n_sheep": 1
+  },
+  {
+    "sr": 0.6333333333333333,
+    "mean_len": 1324.9333333333334,
+    "mean_min_pen": 3.108120004336039,
+    "mean_act": 0.41626948835668365,
+    "failure_modes": {
+      "SUCCESS": 19,
+      "PARTIAL_1of2": 10,
+      "COMPACT_CANT_DRIVE": 1
+    },
+    "reward_per_step": {
+      "progress": 0.045259184195888084,
+      "alignment": 0.006548802090560675,
+      "compact": 0.0,
+      "wall_touch": -0.005243643148915256,
+      "pen_bonus": 0.012327664284995472,
+      "step_cost": -0.019999999999989106,
+      "complete": 0.04780114722753346
+    },
+    "n_sheep": 2
+  },
+  {
+    "sr": 0.9666666666666667,
+    "mean_len": 827.7,
+    "mean_min_pen": 2.727696478366852,
+    "mean_act": 1.1521936838813016,
+    "failure_modes": {
+      "PARTIAL_1of3": 1,
+      "SUCCESS": 29
+    },
+    "reward_per_step": {
+      "progress": 0.10166334638295625,
+      "alignment": 0.013859153429505626,
+      "compact": 0.0,
+      "wall_touch": -0.0022604217500245883,
+      "pen_bonus": 0.03543957150336273,
+      "step_cost": -0.019999999999993488,
+      "complete": 0.11678949699971809
+    },
+    "n_sheep": 3
+  },
+  {
+    "sr": 0.5666666666666667,
+    "mean_len": 1686.0333333333333,
+    "mean_min_pen": 1.7675368865331014,
+    "mean_act": 1.0093803780622697,
+    "failure_modes": {
+      "PARTIAL_1of4": 10,
+      "SUCCESS": 17,
+      "PARTIAL_2of4": 3
+    },
+    "reward_per_step": {
+      "progress": 0.07213990871824405,
+      "alignment": 0.008500170591885925,
+      "compact": 0.0,
+      "wall_touch": -0.01096873654520888,
+      "pen_bonus": 0.016607026353769202,
+      "step_cost": -0.019999999999987545,
+      "complete": 0.03360945809691386
+    },
+    "n_sheep": 4
+  },
+  {
+    "sr": 0.6333333333333333,
+    "mean_len": 1653.8333333333333,
+    "mean_min_pen": 1.6310479640960693,
+    "mean_act": 1.3572492104366454,
+    "failure_modes": {
+      "PARTIAL_2of5": 9,
+      "SUCCESS": 19,
+      "PARTIAL_3of5": 2
+    },
+    "reward_per_step": {
+      "progress": 0.10426509678994506,
+      "alignment": 0.010847962450905363,
+      "compact": 0.0,
+      "wall_touch": -0.010001784418012447,
+      "pen_bonus": 0.02398468205179885,
+      "step_cost": -0.019999999999987656,
+      "complete": 0.038294870502872114
+    },
+    "n_sheep": 5
+  },
+  {
+    "sr": 0.3333333333333333,
+    "mean_len": 2161.0333333333333,
+    "mean_min_pen": 1.7910769859949747,
+    "mean_act": 1.3728399181766682,
+    "failure_modes": {
+      "SUCCESS": 10,
+      "PARTIAL_5of6": 14,
+      "PARTIAL_4of6": 4,
+      "COMPACT_CANT_DRIVE": 2
+    },
+    "reward_per_step": {
+      "progress": 0.09152597398477412,
+      "alignment": 0.010169068168091603,
+      "compact": 0.0,
+      "wall_touch": -0.006849364742307595,
+      "pen_bonus": 0.022520090697351575,
+      "step_cost": -0.019999999999986286,
+      "complete": 0.015424719655720258
+    },
+    "n_sheep": 6
+  },
+  {
+    "sr": 0.2,
+    "mean_len": 2211.2,
+    "mean_min_pen": 1.8339664101600648,
+    "mean_act": 1.3635542380694952,
+    "failure_modes": {
+      "PARTIAL_5of7": 2,
+      "SUCCESS": 6,
+      "PARTIAL_6of7": 3,
+      "PARTIAL_3of7": 8,
+      "PARTIAL_4of7": 11
+    },
+    "reward_per_step": {
+      "progress": 0.08794138462674025,
+      "alignment": 0.008588877237149285,
+      "compact": 0.0,
+      "wall_touch": -0.014176997336213705,
+      "pen_bonus": 0.020803183791606367,
+      "step_cost": -0.019999999999986185,
+      "complete": 0.009044862518089725
+    },
+    "n_sheep": 7
+  },
+  {
+    "sr": 0.6333333333333333,
+    "mean_len": 1744.5666666666666,
+    "mean_min_pen": 1.7331914146741232,
+    "mean_act": 1.366222499606064,
+    "failure_modes": {
+      "SUCCESS": 19,
+      "PARTIAL_4of8": 9,
+      "PARTIAL_1of8": 1,
+      "PARTIAL_6of8": 1
+    },
+    "reward_per_step": {
+      "progress": 0.11981066786559799,
+      "alignment": 0.013385751275637974,
+      "compact": 0.0,
+      "wall_touch": -0.010737474453107049,
+      "pen_bonus": 0.037258536026138295,
+      "step_cost": -0.019999999999987354,
+      "complete": 0.03630318894854501
+    },
+    "n_sheep": 8
+  },
+  {
+    "sr": 0.8333333333333334,
+    "mean_len": 1723.1333333333334,
+    "mean_min_pen": 1.7584208091100058,
+    "mean_act": 1.3848404770822742,
+    "failure_modes": {
+      "NEVER_COMPACT": 1,
+      "SUCCESS": 25,
+      "PARTIAL_5of9": 3,
+      "PARTIAL_6of9": 1
+    },
+    "reward_per_step": {
+      "progress": 0.1561655017464111,
+      "alignment": 0.01548957874142236,
+      "compact": 0.0,
+      "wall_touch": -0.00728069638883058,
+      "pen_bonus": 0.04797461987851588,
+      "step_cost": -0.019999999999987424,
+      "complete": 0.048361511974310364
+    },
+    "n_sheep": 9
+  },
+  {
+    "sr": 0.26666666666666666,
+    "mean_len": 2266.5333333333333,
+    "mean_min_pen": 2.1789512236913047,
+    "mean_act": 1.3836169439830954,
+    "failure_modes": {
+      "PARTIAL_6of10": 16,
+      "SUCCESS": 8,
+      "PARTIAL_7of10": 1,
+      "PARTIAL_9of10": 1,
+      "PARTIAL_5of10": 1,
+      "COMPACT_CANT_DRIVE": 2,
+      "PARTIAL_8of10": 1
+    },
+    "reward_per_step": {
+      "progress": 0.13603502511276877,
+      "alignment": 0.013359252519942029,
+      "compact": 0.0,
+      "wall_touch": -0.012232639033891629,
+      "pen_bonus": 0.030148832284252015,
+      "step_cost": -0.019999999999986078,
+      "complete": 0.011765397964586153
+    },
+    "n_sheep": 10
+  }
+]