Spaces:
Sleeping
Sleeping
Commit ·
d5d74e8
1
Parent(s): e233264
updated weights
Browse files- dashboard.html +9 -2
- results/comparison_results.json +435 -0
- weights/ppo_easy.json +0 -0
- weights/ppo_hard.json +0 -0
- weights/ppo_medium.json +0 -0
dashboard.html
CHANGED
|
@@ -626,10 +626,13 @@ async function fetchRecommendation() {
|
|
| 626 |
}
|
| 627 |
|
| 628 |
async function stepOnce() {
|
| 629 |
-
if (episodeDone
|
|
|
|
|
|
|
| 630 |
// Get recommendation from server (uses trained weights or rule-based)
|
| 631 |
const rec = await fetchRecommendation();
|
| 632 |
if (!rec || rec.error) {
|
|
|
|
| 633 |
showToast('No recommendation available', 'error');
|
| 634 |
return false;
|
| 635 |
}
|
|
@@ -687,7 +690,11 @@ async function autoPlay() {
|
|
| 687 |
document.getElementById('autoBtn').textContent = '⏸ Pause';
|
| 688 |
while (autoPlaying && !episodeDone) {
|
| 689 |
const ok = await stepOnce();
|
| 690 |
-
if (
|
|
|
|
|
|
|
|
|
|
|
|
|
| 691 |
await new Promise(r => setTimeout(r, 300));
|
| 692 |
}
|
| 693 |
autoPlaying = false;
|
|
|
|
| 626 |
}
|
| 627 |
|
| 628 |
async function stepOnce() {
|
| 629 |
+
if (episodeDone) return false;
|
| 630 |
+
if (!currentAlerts.length) return 'wait'; // Queue temporarily empty, wait for environmental spawn
|
| 631 |
+
|
| 632 |
// Get recommendation from server (uses trained weights or rule-based)
|
| 633 |
const rec = await fetchRecommendation();
|
| 634 |
if (!rec || rec.error) {
|
| 635 |
+
if (!currentAlerts.length) return 'wait';
|
| 636 |
showToast('No recommendation available', 'error');
|
| 637 |
return false;
|
| 638 |
}
|
|
|
|
| 690 |
document.getElementById('autoBtn').textContent = '⏸ Pause';
|
| 691 |
while (autoPlaying && !episodeDone) {
|
| 692 |
const ok = await stepOnce();
|
| 693 |
+
if (ok === 'wait') {
|
| 694 |
+
await new Promise(r => setTimeout(r, 1500)); // Queue empty, wait for environmental spawn
|
| 695 |
+
continue;
|
| 696 |
+
}
|
| 697 |
+
if (ok === false) break;
|
| 698 |
await new Promise(r => setTimeout(r, 300));
|
| 699 |
}
|
| 700 |
autoPlaying = false;
|
results/comparison_results.json
ADDED
|
@@ -0,0 +1,435 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"easy": {
|
| 3 |
+
"threshold": 0.7,
|
| 4 |
+
"n_episodes": 10,
|
| 5 |
+
"rule_basic": {
|
| 6 |
+
"mean": 0.565,
|
| 7 |
+
"std": 0.13342705039750288,
|
| 8 |
+
"min": 0.26666666666666666,
|
| 9 |
+
"max": 0.75,
|
| 10 |
+
"success_rate": 0.2,
|
| 11 |
+
"scores": [
|
| 12 |
+
0.6666666666666666,
|
| 13 |
+
0.4666666666666667,
|
| 14 |
+
0.5333333333333333,
|
| 15 |
+
0.6333333333333333,
|
| 16 |
+
0.26666666666666666,
|
| 17 |
+
0.75,
|
| 18 |
+
0.5666666666666667,
|
| 19 |
+
0.6,
|
| 20 |
+
0.4666666666666667,
|
| 21 |
+
0.7
|
| 22 |
+
]
|
| 23 |
+
},
|
| 24 |
+
"rule_improved": {
|
| 25 |
+
"mean": 0.28239130434782606,
|
| 26 |
+
"std": 0.17974288212805087,
|
| 27 |
+
"min": 0.1,
|
| 28 |
+
"max": 0.75,
|
| 29 |
+
"success_rate": 0.1,
|
| 30 |
+
"scores": [
|
| 31 |
+
0.16666666666666666,
|
| 32 |
+
0.2,
|
| 33 |
+
0.1,
|
| 34 |
+
0.4,
|
| 35 |
+
0.13333333333333333,
|
| 36 |
+
0.75,
|
| 37 |
+
0.26666666666666666,
|
| 38 |
+
0.3333333333333333,
|
| 39 |
+
0.17391304347826086,
|
| 40 |
+
0.3
|
| 41 |
+
]
|
| 42 |
+
},
|
| 43 |
+
"ppo": {
|
| 44 |
+
"mean": 0.31885369532428354,
|
| 45 |
+
"std": 0.15685624769000914,
|
| 46 |
+
"min": 0.06666666666666667,
|
| 47 |
+
"max": 0.5,
|
| 48 |
+
"success_rate": 0.0,
|
| 49 |
+
"scores": [
|
| 50 |
+
0.16666666666666666,
|
| 51 |
+
0.5,
|
| 52 |
+
0.5,
|
| 53 |
+
0.26666666666666666,
|
| 54 |
+
0.06666666666666667,
|
| 55 |
+
0.38461538461538464,
|
| 56 |
+
0.23333333333333334,
|
| 57 |
+
0.47058823529411764,
|
| 58 |
+
0.13333333333333333,
|
| 59 |
+
0.4666666666666667
|
| 60 |
+
]
|
| 61 |
+
},
|
| 62 |
+
"training": {
|
| 63 |
+
"episode_rewards": [
|
| 64 |
+
116.48117816744173,
|
| 65 |
+
51.179276131841576,
|
| 66 |
+
52.2618112911265,
|
| 67 |
+
73.2821529517957,
|
| 68 |
+
56.35469617840879,
|
| 69 |
+
80.22612139126159,
|
| 70 |
+
126.40470506929401,
|
| 71 |
+
-27.966666666666665,
|
| 72 |
+
41.83973320279549,
|
| 73 |
+
49.79345637951734
|
| 74 |
+
],
|
| 75 |
+
"episode_scores": [
|
| 76 |
+
0.5666666666666667,
|
| 77 |
+
0.5,
|
| 78 |
+
0.5666666666666667,
|
| 79 |
+
0.5,
|
| 80 |
+
0.43333333333333335,
|
| 81 |
+
0.5666666666666667,
|
| 82 |
+
0.6666666666666666,
|
| 83 |
+
0.1111111111111111,
|
| 84 |
+
0.43333333333333335,
|
| 85 |
+
0.5666666666666667
|
| 86 |
+
],
|
| 87 |
+
"policy_losses": [
|
| 88 |
+
-0.00031701126135885715,
|
| 89 |
+
-0.0005917370435781777,
|
| 90 |
+
-0.0004098603967577219,
|
| 91 |
+
-0.0004132986068725586,
|
| 92 |
+
-0.0011740466579794884,
|
| 93 |
+
-0.0006698071956634521,
|
| 94 |
+
0.0003072003601118922,
|
| 95 |
+
0.0004630155162885785,
|
| 96 |
+
-0.00042602914618328214,
|
| 97 |
+
0.000690912245772779
|
| 98 |
+
],
|
| 99 |
+
"entropies": [
|
| 100 |
+
1.3397215844770598,
|
| 101 |
+
1.28164808620697,
|
| 102 |
+
1.3136498968506878,
|
| 103 |
+
1.3446368176704309,
|
| 104 |
+
1.334242086449483,
|
| 105 |
+
1.3403528217115777,
|
| 106 |
+
1.3486054411454527,
|
| 107 |
+
1.338187676696283,
|
| 108 |
+
1.3261117608663633,
|
| 109 |
+
1.3390974986011028
|
| 110 |
+
]
|
| 111 |
+
}
|
| 112 |
+
},
|
| 113 |
+
"medium": {
|
| 114 |
+
"threshold": 0.55,
|
| 115 |
+
"n_episodes": 15,
|
| 116 |
+
"rule_basic": {
|
| 117 |
+
"mean": 0.6065292,
|
| 118 |
+
"std": 0.1133496138271322,
|
| 119 |
+
"min": 0.407683,
|
| 120 |
+
"max": 0.758043,
|
| 121 |
+
"success_rate": 0.6,
|
| 122 |
+
"scores": [
|
| 123 |
+
0.544947,
|
| 124 |
+
0.608039,
|
| 125 |
+
0.461019,
|
| 126 |
+
0.615249,
|
| 127 |
+
0.407683,
|
| 128 |
+
0.758043,
|
| 129 |
+
0.530671,
|
| 130 |
+
0.731125,
|
| 131 |
+
0.721003,
|
| 132 |
+
0.687513
|
| 133 |
+
]
|
| 134 |
+
},
|
| 135 |
+
"rule_improved": {
|
| 136 |
+
"mean": 0.36824,
|
| 137 |
+
"std": 0.2038091025592331,
|
| 138 |
+
"min": 0.126603,
|
| 139 |
+
"max": 0.731182,
|
| 140 |
+
"success_rate": 0.2,
|
| 141 |
+
"scores": [
|
| 142 |
+
0.126603,
|
| 143 |
+
0.353704,
|
| 144 |
+
0.130989,
|
| 145 |
+
0.731182,
|
| 146 |
+
0.1532,
|
| 147 |
+
0.382268,
|
| 148 |
+
0.284057,
|
| 149 |
+
0.698946,
|
| 150 |
+
0.444375,
|
| 151 |
+
0.377076
|
| 152 |
+
]
|
| 153 |
+
},
|
| 154 |
+
"ppo": {
|
| 155 |
+
"mean": 0.12029260000000001,
|
| 156 |
+
"std": 0.15422419929258832,
|
| 157 |
+
"min": 0.0,
|
| 158 |
+
"max": 0.371589,
|
| 159 |
+
"success_rate": 0.0,
|
| 160 |
+
"scores": [
|
| 161 |
+
0.371589,
|
| 162 |
+
0.0,
|
| 163 |
+
0.0,
|
| 164 |
+
0.327622,
|
| 165 |
+
0.0,
|
| 166 |
+
0.0,
|
| 167 |
+
0.352266,
|
| 168 |
+
0.047619,
|
| 169 |
+
0.0,
|
| 170 |
+
0.10383
|
| 171 |
+
]
|
| 172 |
+
},
|
| 173 |
+
"training": {
|
| 174 |
+
"episode_rewards": [
|
| 175 |
+
289.19607022503374,
|
| 176 |
+
31.324053215893485,
|
| 177 |
+
227.8569682176852,
|
| 178 |
+
69.9986190511277,
|
| 179 |
+
148.51004751942824,
|
| 180 |
+
2.649222740657118,
|
| 181 |
+
142.98109194665278,
|
| 182 |
+
166.0523382428407,
|
| 183 |
+
-17.823338903249397,
|
| 184 |
+
163.79688498101618,
|
| 185 |
+
20.967070078863117,
|
| 186 |
+
252.20290252850012,
|
| 187 |
+
87.20304691964265,
|
| 188 |
+
68.97229783047784,
|
| 189 |
+
48.019239227065704
|
| 190 |
+
],
|
| 191 |
+
"episode_scores": [
|
| 192 |
+
0.747084,
|
| 193 |
+
0.426987,
|
| 194 |
+
0.652915,
|
| 195 |
+
0.572663,
|
| 196 |
+
0.595108,
|
| 197 |
+
0.621572,
|
| 198 |
+
0.575688,
|
| 199 |
+
0.661152,
|
| 200 |
+
0.238471,
|
| 201 |
+
0.599472,
|
| 202 |
+
0.673464,
|
| 203 |
+
0.71291,
|
| 204 |
+
0.510403,
|
| 205 |
+
0.461406,
|
| 206 |
+
0.554831
|
| 207 |
+
],
|
| 208 |
+
"policy_losses": [
|
| 209 |
+
-0.00011090115003753453,
|
| 210 |
+
-0.00045563955791294575,
|
| 211 |
+
-0.0005598295829258859,
|
| 212 |
+
0.0002498215762898326,
|
| 213 |
+
-0.0004835896543227136,
|
| 214 |
+
-0.0002657274599187076,
|
| 215 |
+
2.585202491900418e-05,
|
| 216 |
+
-0.00024676843895576894,
|
| 217 |
+
-4.288851414457895e-06,
|
| 218 |
+
-0.0002753034350462258,
|
| 219 |
+
0.00021128143998794258,
|
| 220 |
+
0.00013167335418984294,
|
| 221 |
+
-0.0014359087217599154,
|
| 222 |
+
0.0001275122194783762,
|
| 223 |
+
-0.0004190042382106185
|
| 224 |
+
],
|
| 225 |
+
"entropies": [
|
| 226 |
+
1.3078774153620452,
|
| 227 |
+
1.3198472053289163,
|
| 228 |
+
1.2824486149720111,
|
| 229 |
+
1.303192149903892,
|
| 230 |
+
1.2968761532941306,
|
| 231 |
+
1.3589913703942351,
|
| 232 |
+
1.3173352639807518,
|
| 233 |
+
1.2921417353749498,
|
| 234 |
+
1.2932024355816831,
|
| 235 |
+
1.2977528110651393,
|
| 236 |
+
1.2935277894985902,
|
| 237 |
+
1.2847667442611173,
|
| 238 |
+
1.2918389386627889,
|
| 239 |
+
1.3078202616228094,
|
| 240 |
+
1.3123808854500285
|
| 241 |
+
]
|
| 242 |
+
}
|
| 243 |
+
},
|
| 244 |
+
"hard": {
|
| 245 |
+
"threshold": 0.5,
|
| 246 |
+
"n_episodes": 30,
|
| 247 |
+
"rule_basic": {
|
| 248 |
+
"mean": 0.3592359,
|
| 249 |
+
"std": 0.04597751458800269,
|
| 250 |
+
"min": 0.305788,
|
| 251 |
+
"max": 0.456861,
|
| 252 |
+
"success_rate": 0.0,
|
| 253 |
+
"scores": [
|
| 254 |
+
0.357113,
|
| 255 |
+
0.344618,
|
| 256 |
+
0.456861,
|
| 257 |
+
0.413206,
|
| 258 |
+
0.305788,
|
| 259 |
+
0.39223,
|
| 260 |
+
0.325218,
|
| 261 |
+
0.324735,
|
| 262 |
+
0.360089,
|
| 263 |
+
0.312501
|
| 264 |
+
]
|
| 265 |
+
},
|
| 266 |
+
"rule_improved": {
|
| 267 |
+
"mean": 0.08083320000000001,
|
| 268 |
+
"std": 0.09074694593737025,
|
| 269 |
+
"min": 0.0,
|
| 270 |
+
"max": 0.330565,
|
| 271 |
+
"success_rate": 0.0,
|
| 272 |
+
"scores": [
|
| 273 |
+
0.073929,
|
| 274 |
+
0.074479,
|
| 275 |
+
0.0,
|
| 276 |
+
0.330565,
|
| 277 |
+
0.077784,
|
| 278 |
+
0.079177,
|
| 279 |
+
0.0,
|
| 280 |
+
0.075606,
|
| 281 |
+
0.0,
|
| 282 |
+
0.096792
|
| 283 |
+
]
|
| 284 |
+
},
|
| 285 |
+
"ppo": {
|
| 286 |
+
"mean": 0.0451608,
|
| 287 |
+
"std": 0.046165539127795314,
|
| 288 |
+
"min": 0.0,
|
| 289 |
+
"max": 0.162508,
|
| 290 |
+
"success_rate": 0.0,
|
| 291 |
+
"scores": [
|
| 292 |
+
0.0,
|
| 293 |
+
0.031159,
|
| 294 |
+
0.070801,
|
| 295 |
+
0.020789,
|
| 296 |
+
0.034032,
|
| 297 |
+
0.03,
|
| 298 |
+
0.162508,
|
| 299 |
+
0.022963,
|
| 300 |
+
0.0,
|
| 301 |
+
0.079356
|
| 302 |
+
]
|
| 303 |
+
},
|
| 304 |
+
"training": {
|
| 305 |
+
"episode_rewards": [
|
| 306 |
+
99.41774516346646,
|
| 307 |
+
52.08058065987078,
|
| 308 |
+
106.23944303643187,
|
| 309 |
+
30.139073873921753,
|
| 310 |
+
56.61845300055894,
|
| 311 |
+
73.32529035534895,
|
| 312 |
+
138.58575407819225,
|
| 313 |
+
-13.80251134755405,
|
| 314 |
+
105.24364041105947,
|
| 315 |
+
143.66845440570685,
|
| 316 |
+
50.946750742115405,
|
| 317 |
+
101.28459645197202,
|
| 318 |
+
44.73084312495516,
|
| 319 |
+
1.5265232947738134,
|
| 320 |
+
-0.5387180214798111,
|
| 321 |
+
33.34359118615684,
|
| 322 |
+
67.93893773141943,
|
| 323 |
+
103.87818539075207,
|
| 324 |
+
141.53997245597657,
|
| 325 |
+
51.56927062513001,
|
| 326 |
+
2.5994465725157045,
|
| 327 |
+
21.409162528947157,
|
| 328 |
+
17.174619999999994,
|
| 329 |
+
122.55731714185875,
|
| 330 |
+
138.50278641960747,
|
| 331 |
+
-4.699999999999999,
|
| 332 |
+
249.20114192274738,
|
| 333 |
+
52.25401551533514,
|
| 334 |
+
79.65609498591343,
|
| 335 |
+
133.96772892643187
|
| 336 |
+
],
|
| 337 |
+
"episode_scores": [
|
| 338 |
+
0.062813,
|
| 339 |
+
0.04039,
|
| 340 |
+
0.122923,
|
| 341 |
+
0.051732,
|
| 342 |
+
0.027002,
|
| 343 |
+
0.042925,
|
| 344 |
+
0.312897,
|
| 345 |
+
0.2,
|
| 346 |
+
0.065612,
|
| 347 |
+
0.046683,
|
| 348 |
+
0.074122,
|
| 349 |
+
0.0,
|
| 350 |
+
0.103474,
|
| 351 |
+
0.039975,
|
| 352 |
+
0.056427,
|
| 353 |
+
0.087705,
|
| 354 |
+
0.027984,
|
| 355 |
+
0.049027,
|
| 356 |
+
0.090291,
|
| 357 |
+
0.095473,
|
| 358 |
+
0.054766,
|
| 359 |
+
0.051002,
|
| 360 |
+
0.069154,
|
| 361 |
+
0.113725,
|
| 362 |
+
0.0,
|
| 363 |
+
0.06,
|
| 364 |
+
0.347106,
|
| 365 |
+
0.095914,
|
| 366 |
+
0.116824,
|
| 367 |
+
0.069492
|
| 368 |
+
],
|
| 369 |
+
"policy_losses": [
|
| 370 |
+
-0.0005034402711316943,
|
| 371 |
+
-6.183655932545662e-05,
|
| 372 |
+
0.00035082444082945585,
|
| 373 |
+
-0.00038212965591810644,
|
| 374 |
+
-0.00010332465171813965,
|
| 375 |
+
-0.00020747099188156426,
|
| 376 |
+
-0.00016732812218833715,
|
| 377 |
+
-0.00014956295490264893,
|
| 378 |
+
-0.0003894716501235962,
|
| 379 |
+
0.00039730468415655196,
|
| 380 |
+
0.0008679513703100383,
|
| 381 |
+
0.0003810872440226376,
|
| 382 |
+
0.0004052993026562035,
|
| 383 |
+
-0.0002230490936199203,
|
| 384 |
+
-0.0003821717400569469,
|
| 385 |
+
-0.0010335743427276611,
|
| 386 |
+
0.00025102682411670685,
|
| 387 |
+
0.00039608514634892344,
|
| 388 |
+
0.00023010990116745234,
|
| 389 |
+
-0.0010765307815745473,
|
| 390 |
+
-0.0007117217173799872,
|
| 391 |
+
-0.0006123952916823328,
|
| 392 |
+
-0.0017230421071872115,
|
| 393 |
+
0.000159939139848575,
|
| 394 |
+
2.03229756152723e-05,
|
| 395 |
+
-0.0015492378734052181,
|
| 396 |
+
-0.0004421842168085277,
|
| 397 |
+
-0.00029417508631013334,
|
| 398 |
+
9.047671483131126e-05,
|
| 399 |
+
0.00019198372319806367
|
| 400 |
+
],
|
| 401 |
+
"entropies": [
|
| 402 |
+
1.3224266713118111,
|
| 403 |
+
1.293569102812929,
|
| 404 |
+
1.2913357524537528,
|
| 405 |
+
1.3050642097992904,
|
| 406 |
+
1.3112657711037068,
|
| 407 |
+
1.2895643985942957,
|
| 408 |
+
1.3155195660204368,
|
| 409 |
+
1.359707747865233,
|
| 410 |
+
1.2949677676487992,
|
| 411 |
+
1.2961893168835212,
|
| 412 |
+
1.2964495135329652,
|
| 413 |
+
1.3035501102717268,
|
| 414 |
+
1.3021071611669996,
|
| 415 |
+
1.2931140090628328,
|
| 416 |
+
1.300373082313374,
|
| 417 |
+
1.2937277936176361,
|
| 418 |
+
1.28773486772252,
|
| 419 |
+
1.310148409601071,
|
| 420 |
+
1.288673149660661,
|
| 421 |
+
1.325662991150635,
|
| 422 |
+
1.293254712167581,
|
| 423 |
+
1.2945157631549828,
|
| 424 |
+
1.3166287955261984,
|
| 425 |
+
1.298098445695401,
|
| 426 |
+
1.2962819506837526,
|
| 427 |
+
1.2905327485365072,
|
| 428 |
+
1.318213829711901,
|
| 429 |
+
1.326138970673737,
|
| 430 |
+
1.3073734220909363,
|
| 431 |
+
1.3123867051662546
|
| 432 |
+
]
|
| 433 |
+
}
|
| 434 |
+
}
|
| 435 |
+
}
|
weights/ppo_easy.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
weights/ppo_hard.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
weights/ppo_medium.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|