莫烦python中的DDPG运行结果

最新推荐文章于 2023-02-06 18:01:13 发布
最新推荐文章于 2023-02-06 18:01:13 发布
阅读量3k 收藏 5
点赞数
分类专栏： python函数学习
版权声明：本文为博主原创文章，遵循 CC 4.0 BY-SA 版权协议，转载请附上原文出处链接和本声明。
本文链接：https://blog.csdn.net/weixin_42828571/article/details/105300511
版权

文章目录

1、DDPG.py（267行）

/home/fyo/anaconda3/envs/py35/bin/python /home/fyo/PycharmProjects/MOFAN/Reinforcement-learning-with-tensorflow-master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG.py
/home/fyo/anaconda3/envs/py35/lib/python3.5/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
  warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
2020-04-03 20:31:19.950583: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-04-03 20:31:19.952073: I tensorflow/core/common_runtime/process_util.cc:63] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Episode: 0  Reward: -1271 Explore: 3.00
Episode: 1  Reward: -1300 Explore: 3.00
Episode: 2  Reward: -1238 Explore: 3.00
Episode: 3  Reward: -1480 Explore: 3.00
Episode: 4  Reward: -1423 Explore: 3.00
Episode: 5  Reward: -1664 Explore: 3.00
Episode: 6  Reward: -1115 Explore: 3.00
Episode: 7  Reward: -1179 Explore: 3.00
Episode: 8  Reward: -1168 Explore: 3.00
Episode: 9  Reward: -1043 Explore: 3.00
Episode: 10  Reward: -1261 Explore: 3.00
Episode: 11  Reward: -1133 Explore: 3.00
Episode: 12  Reward: -1810 Explore: 3.00
Episode: 13  Reward: -1196 Explore: 3.00
Episode: 14  Reward: -1274 Explore: 3.00
Episode: 15  Reward: -1518 Explore: 3.00
Episode: 16  Reward: -1331 Explore: 3.00
Episode: 17  Reward: -1247 Explore: 3.00
Episode: 18  Reward: -1338 Explore: 3.00
Episode: 19  Reward: -1413 Explore: 3.00
Episode: 20  Reward: -1605 Explore: 3.00
Episode: 21  Reward: -1197 Explore: 3.00
Episode: 22  Reward: -1340 Explore: 3.00
Episode: 23  Reward: -1686 Explore: 3.00
Episode: 24  Reward: -1367 Explore: 3.00
Episode: 25  Reward: -1251 Explore: 3.00
Episode: 26  Reward: -1128 Explore: 3.00
Episode: 27  Reward: -1170 Explore: 3.00
Episode: 28  Reward: -1274 Explore: 3.00
Episode: 29  Reward: -1129 Explore: 3.00
Episode: 30  Reward: -1269 Explore: 3.00
Episode: 31  Reward: -1189 Explore: 3.00
Episode: 32  Reward: -1325 Explore: 3.00
Episode: 33  Reward: -1338 Explore: 3.00
Episode: 34  Reward: -1199 Explore: 3.00
Episode: 35  Reward: -1311 Explore: 3.00
Episode: 36  Reward: -1202 Explore: 3.00
Episode: 37  Reward: -1137 Explore: 3.00
Episode: 38  Reward: -1092 Explore: 3.00
Episode: 39  Reward: -1177 Explore: 3.00
Episode: 40  Reward: -1298 Explore: 3.00
Episode: 41  Reward: -1250 Explore: 3.00
Episode: 42  Reward: -1056 Explore: 3.00
Episode: 43  Reward: -1178 Explore: 3.00
Episode: 44  Reward: -1235 Explore: 3.00
Episode: 45  Reward: -1513 Explore: 3.00
Episode: 46  Reward: -1344 Explore: 3.00
Episode: 47  Reward: -1633 Explore: 3.00
Episode: 48  Reward: -1289 Explore: 3.00
Episode: 49  Reward: -1595 Explore: 3.00
Episode: 50  Reward: -1312 Explore: 2.71
Episode: 51  Reward: -1295 Explore: 2.46
Episode: 52  Reward: -1325 Explore: 2.22
Episode: 53  Reward: -1298 Explore: 2.01
Episode: 54  Reward: -1608 Explore: 1.82
Episode: 55  Reward: -1111 Explore: 1.65
Episode: 56  Reward: -1309 Explore: 1.49
Episode: 57  Reward: -1516 Explore: 1.35
Episode: 58  Reward: -1505 Explore: 1.22
Episode: 59  Reward: -1132 Explore: 1.10
Episode: 60  Reward: -1265 Explore: 1.00
Episode: 61  Reward: -1320 Explore: 0.90
Episode: 62  Reward: -1470 Explore: 0.82
Episode: 63  Reward: -1545 Explore: 0.74
Episode: 64  Reward: -1251 Explore: 0.67
Episode: 65  Reward: -1375 Explore: 0.61
Episode: 66  Reward: -1169 Explore: 0.55
Episode: 67  Reward: -1549 Explore: 0.50
Episode: 68  Reward: -1554 Explore: 0.45
Episode: 69  Reward: -1535 Explore: 0.41
Episode: 70  Reward: -1633 Explore: 0.37
Episode: 71  Reward: -1547 Explore: 0.33
Episode: 72  Reward: -1287 Explore: 0.30
Episode: 73  Reward: -1161 Explore: 0.27
Episode: 74  Reward: -1628 Explore: 0.25
Episode: 75  Reward: -1095 Explore: 0.22
Episode: 76  Reward: -1382 Explore: 0.20
Episode: 77  Reward: -1647 Explore: 0.18
Episode: 78  Reward: -1514 Explore: 0.16
Episode: 79  Reward: -1211 Explore: 0.15
Episode: 80  Reward: -1513 Explore: 0.14
Episode: 81  Reward: -1543 Explore: 0.12
Episode: 82  Reward: -1501 Explore: 0.11
Episode: 83  Reward: -1459 Explore: 0.10
Episode: 84  Reward: -945 Explore: 0.09
Episode: 85  Reward: -1616 Explore: 0.08
Episode: 86  Reward: -1642 Explore: 0.07
Episode: 87  Reward: -1639 Explore: 0.07
Episode: 88  Reward: -1647 Explore: 0.06
Episode: 89  Reward: -1189 Explore: 0.05
Episode: 90  Reward: -1499 Explore: 0.05
Episode: 91  Reward: -1158 Explore: 0.04
Episode: 92  Reward: -1332 Explore: 0.04
Episode: 93  Reward: -1654 Explore: 0.04
Episode: 94  Reward: -1549 Explore: 0.03
Episode: 95  Reward: -1339 Explore: 0.03
Episode: 96  Reward: -1646 Explore: 0.03
Episode: 97  Reward: -1058 Explore: 0.02
Episode: 98  Reward: -721 Explore: 0.02
Episode: 99  Reward: -1474 Explore: 0.02
Episode: 100  Reward: -1525 Explore: 0.02
Episode: 101  Reward: -1631 Explore: 0.02
Episode: 102  Reward: -1494 Explore: 0.01
Episode: 103  Reward: -1607 Explore: 0.01
Episode: 104  Reward: -1608 Explore: 0.01
Episode: 105  Reward: -1562 Explore: 0.01
Episode: 106  Reward: -1520 Explore: 0.01
Episode: 107  Reward: -1119 Explore: 0.01
Episode: 108  Reward: -1365 Explore: 0.01
Episode: 109  Reward: -1136 Explore: 0.01
Episode: 110  Reward: -937 Explore: 0.01
Episode: 111  Reward: -1278 Explore: 0.01
Episode: 112  Reward: -1502 Explore: 0.01
Episode: 113  Reward: -1616 Explore: 0.00
Episode: 114  Reward: -1537 Explore: 0.00
Episode: 115  Reward: -1476 Explore: 0.00
Episode: 116  Reward: -1377 Explore: 0.00
Episode: 117  Reward: -1502 Explore: 0.00
Episode: 118  Reward: -1633 Explore: 0.00
Episode: 119  Reward: -1315 Explore: 0.00
Episode: 120  Reward: -1634 Explore: 0.00
Episode: 121  Reward: -1302 Explore: 0.00
Episode: 122  Reward: -1278 Explore: 0.00
Episode: 123  Reward: -1621 Explore: 0.00
Episode: 124  Reward: -1108 Explore: 0.00
Episode: 125  Reward: -1207 Explore: 0.00
Episode: 126  Reward: -1641 Explore: 0.00
Episode: 127  Reward: -838 Explore: 0.00
Episode: 128  Reward: -1551 Explore: 0.00
Episode: 129  Reward: -1568 Explore: 0.00
Episode: 130  Reward: -1540 Explore: 0.00
Episode: 131  Reward: -1510 Explore: 0.00
Episode: 132  Reward: -1292 Explore: 0.00
Episode: 133  Reward: -1648 Explore: 0.00
Episode: 134  Reward: -1490 Explore: 0.00
Episode: 135  Reward: -1654 Explore: 0.00
Episode: 136  Reward: -1503 Explore: 0.00
Episode: 137  Reward: -1397 Explore: 0.00
Episode: 138  Reward: -1345 Explore: 0.00
Episode: 139  Reward: -1283 Explore: 0.00
Episode: 140  Reward: -1286 Explore: 0.00
Episode: 141  Reward: -1483 Explore: 0.00
Episode: 142  Reward: -1651 Explore: 0.00
Episode: 143  Reward: -954 Explore: 0.00
Episode: 144  Reward: -1653 Explore: 0.00
Episode: 145  Reward: -1010 Explore: 0.00
Episode: 146  Reward: -1491 Explore: 0.00
Episode: 147  Reward: -1360 Explore: 0.00
Episode: 148  Reward: -1494 Explore: 0.00
Episode: 149  Reward: -1196 Explore: 0.00
Episode: 150  Reward: -1593 Explore: 0.00
Episode: 151  Reward: -1494 Explore: 0.00
Episode: 152  Reward: -1506 Explore: 0.00
Episode: 153  Reward: -1569 Explore: 0.00
Episode: 154  Reward: -1407 Explore: 0.00
Episode: 155  Reward: -1133 Explore: 0.00
Episode: 156  Reward: -1502 Explore: 0.00
Episode: 157  Reward: -1330 Explore: 0.00
Episode: 158  Reward: -1654 Explore: 0.00
Episode: 159  Reward: -1438 Explore: 0.00
Episode: 160  Reward: -1642 Explore: 0.00
Episode: 161  Reward: -1504 Explore: 0.00
Episode: 162  Reward: -1657 Explore: 0.00
Episode: 163  Reward: -1637 Explore: 0.00
Episode: 164  Reward: -1243 Explore: 0.00
Episode: 165  Reward: -1053 Explore: 0.00
Episode: 166  Reward: -1511 Explore: 0.00
Episode: 167  Reward: -1623 Explore: 0.00
Episode: 168  Reward: -1067 Explore: 0.00
Episode: 169  Reward: -946 Explore: 0.00
Episode: 170  Reward: -1433 Explore: 0.00
Episode: 171  Reward: -1495 Explore: 0.00
Episode: 172  Reward: -1656 Explore: 0.00
Episode: 173  Reward: -1651 Explore: 0.00
Episode: 174  Reward: -1656 Explore: 0.00
Episode: 175  Reward: -1036 Explore: 0.00
Episode: 176  Reward: -1629 Explore: 0.00
Episode: 177  Reward: -1219 Explore: 0.00
Episode: 178  Reward: -1218 Explore: 0.00
Episode: 179  Reward: -1213 Explore: 0.00
Episode: 180  Reward: -1652 Explore: 0.00
Episode: 181  Reward: -1516 Explore: 0.00
Episode: 182  Reward: -922 Explore: 0.00
Episode: 183  Reward: -947 Explore: 0.00
Episode: 184  Reward: -1389 Explore: 0.00
Episode: 185  Reward: -1346 Explore: 0.00
Episode: 186  Reward: -1112 Explore: 0.00
Episode: 187  Reward: -1650 Explore: 0.00
Episode: 188  Reward: -939 Explore: 0.00
Episode: 189  Reward: -1638 Explore: 0.00
Episode: 190  Reward: -1274 Explore: 0.00
Episode: 191  Reward: -1495 Explore: 0.00
Episode: 192  Reward: -1645 Explore: 0.00
Episode: 193  Reward: -1533 Explore: 0.00
Episode: 194  Reward: -1491 Explore: 0.00
Episode: 195  Reward: -1533 Explore: 0.00
Episode: 196  Reward: -1420 Explore: 0.00
Episode: 197  Reward: -1625 Explore: 0.00
Episode: 198  Reward: -1409 Explore: 0.00
Episode: 199  Reward: -1480 Explore: 0.00
Running time:  160.86654114723206

2、DDPG_update.py（151行）

/home/fyo/anaconda3/envs/py35/bin/python /home/fyo/PycharmProjects/MOFAN/Reinforcement-learning-with-tensorflow-master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update.py
/home/fyo/anaconda3/envs/py35/lib/python3.5/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
  warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
2020-04-03 20:17:24.242517: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-04-03 20:17:24.246205: I tensorflow/core/common_runtime/process_util.cc:63] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Episode: 0  Reward: -1457 Explore: 3.00
Episode: 1  Reward: -1513 Explore: 3.00
Episode: 2  Reward: -1490 Explore: 3.00
Episode: 3  Reward: -1550 Explore: 3.00
Episode: 4  Reward: -1481 Explore: 3.00
Episode: 5  Reward: -1645 Explore: 3.00
Episode: 6  Reward: -1627 Explore: 3.00
Episode: 7  Reward: -1570 Explore: 3.00
Episode: 8  Reward: -1178 Explore: 3.00
Episode: 9  Reward: -1665 Explore: 3.00
Episode: 10  Reward: -1074 Explore: 3.00
Episode: 11  Reward: -1536 Explore: 3.00
Episode: 12  Reward: -1659 Explore: 3.00
Episode: 13  Reward: -1512 Explore: 3.00
Episode: 14  Reward: -1350 Explore: 3.00
Episode: 15  Reward: -1748 Explore: 3.00
Episode: 16  Reward: -1553 Explore: 3.00
Episode: 17  Reward: -1393 Explore: 3.00
Episode: 18  Reward: -1504 Explore: 3.00
Episode: 19  Reward: -1620 Explore: 3.00
Episode: 20  Reward: -1660 Explore: 3.00
Episode: 21  Reward: -1461 Explore: 3.00
Episode: 22  Reward: -1402 Explore: 3.00
Episode: 23  Reward: -1635 Explore: 3.00
Episode: 24  Reward: -1431 Explore: 3.00
Episode: 25  Reward: -1567 Explore: 3.00
Episode: 26  Reward: -1569 Explore: 3.00
Episode: 27  Reward: -1488 Explore: 3.00
Episode: 28  Reward: -1193 Explore: 3.00
Episode: 29  Reward: -1332 Explore: 3.00
Episode: 30  Reward: -1169 Explore: 3.00
Episode: 31  Reward: -1613 Explore: 3.00
Episode: 32  Reward: -1259 Explore: 3.00
Episode: 33  Reward: -1311 Explore: 3.00
Episode: 34  Reward: -1409 Explore: 3.00
Episode: 35  Reward: -1445 Explore: 3.00
Episode: 36  Reward: -1441 Explore: 3.00
Episode: 37  Reward: -1202 Explore: 3.00
Episode: 38  Reward: -1543 Explore: 3.00
Episode: 39  Reward: -1433 Explore: 3.00
Episode: 40  Reward: -1344 Explore: 3.00
Episode: 41  Reward: -1655 Explore: 3.00
Episode: 42  Reward: -1453 Explore: 3.00
Episode: 43  Reward: -1444 Explore: 3.00
Episode: 44  Reward: -1153 Explore: 3.00
Episode: 45  Reward: -1568 Explore: 3.00
Episode: 46  Reward: -899 Explore: 3.00
Episode: 47  Reward: -1662 Explore: 3.00
Episode: 48  Reward: -1074 Explore: 3.00
Episode: 49  Reward: -1632 Explore: 3.00
Episode: 50  Reward: -1133 Explore: 2.71
Episode: 51  Reward: -1043 Explore: 2.46
Episode: 52  Reward: -1326 Explore: 2.22
Episode: 53  Reward: -1367 Explore: 2.01
Episode: 54  Reward: -1407 Explore: 1.82
Episode: 55  Reward: -1222 Explore: 1.65
Episode: 56  Reward: -1158 Explore: 1.49
Episode: 57  Reward: -1096 Explore: 1.35
Episode: 58  Reward: -854 Explore: 1.22
Episode: 59  Reward: -658 Explore: 1.10
Episode: 60  Reward: -915 Explore: 1.00
Episode: 61  Reward: -1283 Explore: 0.90
Episode: 62  Reward: -569 Explore: 0.82
Episode: 63  Reward: -261 Explore: 0.74
Episode: 64  Reward: -262 Explore: 0.67
Episode: 65  Reward: -387 Explore: 0.61
Episode: 66  Reward: -389 Explore: 0.55
Episode: 67  Reward: -386 Explore: 0.50
Episode: 68  Reward: -376 Explore: 0.45
Episode: 69  Reward: -382 Explore: 0.41
Episode: 70  Reward: -259 Explore: 0.37
Episode: 71  Reward: -390 Explore: 0.33
Episode: 72  Reward: -135 Explore: 0.30
Episode: 73  Reward: -128 Explore: 0.27
Episode: 74  Reward: -264 Explore: 0.25
Episode: 75  Reward: -275 Explore: 0.22
Episode: 76  Reward: -360 Explore: 0.20
Episode: 77  Reward: -262 Explore: 0.18
Episode: 78  Reward: -363 Explore: 0.16
Episode: 79  Reward: -252 Explore: 0.15
Episode: 80  Reward: -366 Explore: 0.14
Episode: 81  Reward: -1 Explore: 0.12
Episode: 82  Reward: -268 Explore: 0.11
Episode: 83  Reward: -364 Explore: 0.10
Episode: 84  Reward: -130 Explore: 0.09
Episode: 85  Reward: -125 Explore: 0.08
Episode: 86  Reward: -133 Explore: 0.07
Episode: 87  Reward: -127 Explore: 0.07
Episode: 88  Reward: -137 Explore: 0.06
Episode: 89  Reward: -137 Explore: 0.05
Episode: 90  Reward: -265 Explore: 0.05
Episode: 91  Reward: -854 Explore: 0.04
Episode: 92  Reward: -133 Explore: 0.04
Episode: 93  Reward: -130 Explore: 0.04
Episode: 94  Reward: -1 Explore: 0.03
Episode: 95  Reward: -131 Explore: 0.03
Episode: 96  Reward: -133 Explore: 0.03
Episode: 97  Reward: -130 Explore: 0.02
Episode: 98  Reward: -132 Explore: 0.02
Episode: 99  Reward: -381 Explore: 0.02
Episode: 100  Reward: -249 Explore: 0.02
Episode: 101  Reward: -134 Explore: 0.02
Episode: 102  Reward: -358 Explore: 0.01
Episode: 103  Reward: -4 Explore: 0.01
Episode: 104  Reward: -133 Explore: 0.01
Episode: 105  Reward: -8 Explore: 0.01
Episode: 106  Reward: -7 Explore: 0.01
Episode: 107  Reward: -130 Explore: 0.01
Episode: 108  Reward: -390 Explore: 0.01
Episode: 109  Reward: -134 Explore: 0.01
Episode: 110  Reward: -133 Explore: 0.01
Episode: 111  Reward: -132 Explore: 0.01
Episode: 112  Reward: -380 Explore: 0.01
Episode: 113  Reward: -143 Explore: 0.00
Episode: 114  Reward: -3 Explore: 0.00
Episode: 115  Reward: -379 Explore: 0.00
Episode: 116  Reward: -381 Explore: 0.00
Episode: 117  Reward: -251 Explore: 0.00
Episode: 118  Reward: -3 Explore: 0.00
Episode: 119  Reward: -437 Explore: 0.00
Episode: 120  Reward: -269 Explore: 0.00
Episode: 121  Reward: -409 Explore: 0.00
Episode: 122  Reward: -536 Explore: 0.00
Episode: 123  Reward: -6 Explore: 0.00
Episode: 124  Reward: -141 Explore: 0.00
Episode: 125  Reward: -141 Explore: 0.00
Episode: 126  Reward: -278 Explore: 0.00
Episode: 127  Reward: -292 Explore: 0.00
Episode: 128  Reward: -1 Explore: 0.00
Episode: 129  Reward: -1 Explore: 0.00
Episode: 130  Reward: 0 Explore: 0.00
Episode: 131  Reward: -282 Explore: 0.00
Episode: 132  Reward: -124 Explore: 0.00
Episode: 133  Reward: -130 Explore: 0.00
Episode: 134  Reward: -1007 Explore: 0.00
Episode: 135  Reward: -980 Explore: 0.00
Episode: 136  Reward: -258 Explore: 0.00
Episode: 137  Reward: -115 Explore: 0.00
Episode: 138  Reward: -266 Explore: 0.00
Episode: 139  Reward: -368 Explore: 0.00
Episode: 140  Reward: -133 Explore: 0.00
Episode: 141  Reward: -532 Explore: 0.00
Episode: 142  Reward: -272 Explore: 0.00
Episode: 143  Reward: -530 Explore: 0.00
Episode: 144  Reward: -393 Explore: 0.00
Episode: 145  Reward: -400 Explore: 0.00
Episode: 146  Reward: -500 Explore: 0.00
Episode: 147  Reward: -269 Explore: 0.00
Episode: 148  Reward: -528 Explore: 0.00
Episode: 149  Reward: -135 Explore: 0.00
Episode: 150  Reward: -169 Explore: 0.00
Episode: 151  Reward: -381 Explore: 0.00
Episode: 152  Reward: -285 Explore: 0.00
Episode: 153  Reward: -12 Explore: 0.00
Episode: 154  Reward: -361 Explore: 0.00
Episode: 155  Reward: -130 Explore: 0.00
Episode: 156  Reward: -533 Explore: 0.00
Episode: 157  Reward: -449 Explore: 0.00
Episode: 158  Reward: -376 Explore: 0.00
Episode: 159  Reward: -519 Explore: 0.00
Episode: 160  Reward: -390 Explore: 0.00
Episode: 161  Reward: -552 Explore: 0.00
Episode: 162  Reward: -423 Explore: 0.00
Episode: 163  Reward: -267 Explore: 0.00
Episode: 164  Reward: -131 Explore: 0.00
Episode: 165  Reward: -384 Explore: 0.00
Episode: 166  Reward: -1225 Explore: 0.00
Episode: 167  Reward: -644 Explore: 0.00
Episode: 168  Reward: -253 Explore: 0.00
Episode: 169  Reward: -134 Explore: 0.00
Episode: 170  Reward: -409 Explore: 0.00
Episode: 171  Reward: -679 Explore: 0.00
Episode: 172  Reward: -133 Explore: 0.00
Episode: 173  Reward: -128 Explore: 0.00
Episode: 174  Reward: -125 Explore: 0.00
Episode: 175  Reward: -130 Explore: 0.00
Episode: 176  Reward: -135 Explore: 0.00
Episode: 177  Reward: -132 Explore: 0.00
Episode: 178  Reward: -133 Explore: 0.00
Episode: 179  Reward: -130 Explore: 0.00
Episode: 180  Reward: -129 Explore: 0.00
Episode: 181  Reward: -267 Explore: 0.00
Episode: 182  Reward: -132 Explore: 0.00
Episode: 183  Reward: -130 Explore: 0.00
Episode: 184  Reward: -488 Explore: 0.00
Episode: 185  Reward: -133 Explore: 0.00
Episode: 186  Reward: -130 Explore: 0.00
Episode: 187  Reward: -129 Explore: 0.00
Episode: 188  Reward: -133 Explore: 0.00
Episode: 189  Reward: -133 Explore: 0.00
Episode: 190  Reward: -1503 Explore: 0.00
Episode: 191  Reward: -421 Explore: 0.00
Episode: 192  Reward: -132 Explore: 0.00
Episode: 193  Reward: -2 Explore: 0.00
Episode: 194  Reward: -401 Explore: 0.00
Episode: 195  Reward: -272 Explore: 0.00
Episode: 196  Reward: -122 Explore: 0.00
Episode: 197  Reward: 0 Explore: 0.00
Episode: 198  Reward: -123 Explore: 0.00
Episode: 199  Reward: -247 Explore: 0.00
Running time:  187.92221856117249

3、DDPG_update2.py（152行）

/home/fyo/anaconda3/envs/py35/bin/python /home/fyo/PycharmProjects/MOFAN/Reinforcement-learning-with-tensorflow-master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG/DDPG_update2.py
/home/fyo/anaconda3/envs/py35/lib/python3.5/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32
  warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow'))
2020-04-03 20:27:37.005980: I tensorflow/core/platform/cpu_feature_guard.cc:140] Your CPU supports instructions that this TensorFlow binary was not compiled to use: SSE4.1 SSE4.2 AVX AVX2 FMA
2020-04-03 20:27:37.007911: I tensorflow/core/common_runtime/process_util.cc:63] Creating new thread pool with default inter op setting: 2. Tune using inter_op_parallelism_threads for best performance.
Episode: 0  Reward: -1096 Explore: 3.00
Episode: 1  Reward: -1213 Explore: 3.00
Episode: 2  Reward: -1284 Explore: 3.00
Episode: 3  Reward: -1780 Explore: 3.00
Episode: 4  Reward: -1188 Explore: 3.00
Episode: 5  Reward: -1367 Explore: 3.00
Episode: 6  Reward: -1165 Explore: 3.00
Episode: 7  Reward: -1303 Explore: 3.00
Episode: 8  Reward: -1184 Explore: 3.00
Episode: 9  Reward: -1099 Explore: 3.00
Episode: 10  Reward: -1327 Explore: 3.00
Episode: 11  Reward: -1232 Explore: 3.00
Episode: 12  Reward: -1640 Explore: 3.00
Episode: 13  Reward: -1279 Explore: 3.00
Episode: 14  Reward: -1247 Explore: 3.00
Episode: 15  Reward: -1476 Explore: 3.00
Episode: 16  Reward: -1338 Explore: 3.00
Episode: 17  Reward: -1360 Explore: 3.00
Episode: 18  Reward: -1099 Explore: 3.00
Episode: 19  Reward: -1332 Explore: 3.00
Episode: 20  Reward: -1414 Explore: 3.00
Episode: 21  Reward: -1245 Explore: 3.00
Episode: 22  Reward: -1342 Explore: 3.00
Episode: 23  Reward: -1499 Explore: 3.00
Episode: 24  Reward: -1157 Explore: 3.00
Episode: 25  Reward: -1206 Explore: 3.00
Episode: 26  Reward: -1285 Explore: 3.00
Episode: 27  Reward: -1218 Explore: 3.00
Episode: 28  Reward: -1317 Explore: 3.00
Episode: 29  Reward: -1351 Explore: 3.00
Episode: 30  Reward: -1262 Explore: 3.00
Episode: 31  Reward: -1294 Explore: 3.00
Episode: 32  Reward: -1174 Explore: 3.00
Episode: 33  Reward: -1189 Explore: 3.00
Episode: 34  Reward: -1199 Explore: 3.00
Episode: 35  Reward: -1282 Explore: 3.00
Episode: 36  Reward: -1302 Explore: 3.00
Episode: 37  Reward: -1087 Explore: 3.00
Episode: 38  Reward: -1281 Explore: 3.00
Episode: 39  Reward: -1107 Explore: 3.00
Episode: 40  Reward: -1175 Explore: 3.00
Episode: 41  Reward: -1408 Explore: 3.00
Episode: 42  Reward: -1190 Explore: 3.00
Episode: 43  Reward: -1232 Explore: 3.00
Episode: 44  Reward: -1128 Explore: 3.00
Episode: 45  Reward: -1796 Explore: 3.00
Episode: 46  Reward: -1188 Explore: 3.00
Episode: 47  Reward: -1622 Explore: 3.00
Episode: 48  Reward: -1353 Explore: 3.00
Episode: 49  Reward: -1537 Explore: 3.00
Episode: 50  Reward: -1279 Explore: 2.71
Episode: 51  Reward: -1325 Explore: 2.46
Episode: 52  Reward: -1632 Explore: 2.22
Episode: 53  Reward: -1557 Explore: 2.01
Episode: 54  Reward: -1651 Explore: 1.82
Episode: 55  Reward: -1267 Explore: 1.65
Episode: 56  Reward: -1141 Explore: 1.49
Episode: 57  Reward: -1103 Explore: 1.35
Episode: 58  Reward: -1294 Explore: 1.22
Episode: 59  Reward: -1507 Explore: 1.10
Episode: 60  Reward: -1330 Explore: 1.00
Episode: 61  Reward: -641 Explore: 0.90
Episode: 62  Reward: -1039 Explore: 0.82
Episode: 63  Reward: -888 Explore: 0.74
Episode: 64  Reward: -876 Explore: 0.67
Episode: 65  Reward: -897 Explore: 0.61
Episode: 66  Reward: -886 Explore: 0.55
Episode: 67  Reward: -958 Explore: 0.50
Episode: 68  Reward: -902 Explore: 0.45
Episode: 69  Reward: -905 Explore: 0.41
Episode: 70  Reward: -655 Explore: 0.37
Episode: 71  Reward: -272 Explore: 0.33
Episode: 72  Reward: -267 Explore: 0.30
Episode: 73  Reward: -259 Explore: 0.27
Episode: 74  Reward: -133 Explore: 0.25
Episode: 75  Reward: -400 Explore: 0.22
Episode: 76  Reward: -467 Explore: 0.20
Episode: 77  Reward: -126 Explore: 0.18
Episode: 78  Reward: -364 Explore: 0.16
Episode: 79  Reward: -376 Explore: 0.15
Episode: 80  Reward: -362 Explore: 0.14
Episode: 81  Reward: 0 Explore: 0.12
Episode: 82  Reward: -392 Explore: 0.11
Episode: 83  Reward: -486 Explore: 0.10
Episode: 84  Reward: -258 Explore: 0.09
Episode: 85  Reward: -121 Explore: 0.08
Episode: 86  Reward: -131 Explore: 0.07
Episode: 87  Reward: -122 Explore: 0.07
Episode: 88  Reward: -130 Explore: 0.06
Episode: 89  Reward: -135 Explore: 0.05
Episode: 90  Reward: -257 Explore: 0.05
Episode: 91  Reward: -131 Explore: 0.04
Episode: 92  Reward: -131 Explore: 0.04
Episode: 93  Reward: -128 Explore: 0.04
Episode: 94  Reward: -2 Explore: 0.03
Episode: 95  Reward: -256 Explore: 0.03
Episode: 96  Reward: -129 Explore: 0.03
Episode: 97  Reward: -127 Explore: 0.02
Episode: 98  Reward: -264 Explore: 0.02
Episode: 99  Reward: -382 Explore: 0.02
Episode: 100  Reward: -246 Explore: 0.02
Episode: 101  Reward: -130 Explore: 0.02
Episode: 102  Reward: -369 Explore: 0.01
Episode: 103  Reward: -1 Explore: 0.01
Episode: 104  Reward: -123 Explore: 0.01
Episode: 105  Reward: -1 Explore: 0.01
Episode: 106  Reward: -3 Explore: 0.01
Episode: 107  Reward: -125 Explore: 0.01
Episode: 108  Reward: -256 Explore: 0.01
Episode: 109  Reward: -136 Explore: 0.01
Episode: 110  Reward: -133 Explore: 0.01
Episode: 111  Reward: -132 Explore: 0.01
Episode: 112  Reward: -671 Explore: 0.01
Episode: 113  Reward: -687 Explore: 0.00
Episode: 114  Reward: -654 Explore: 0.00
Episode: 115  Reward: -950 Explore: 0.00
Episode: 116  Reward: -949 Explore: 0.00
Episode: 117  Reward: -1300 Explore: 0.00
Episode: 118  Reward: -1389 Explore: 0.00
Episode: 119  Reward: -1171 Explore: 0.00
Episode: 120  Reward: -397 Explore: 0.00
Episode: 121  Reward: -348 Explore: 0.00
Episode: 122  Reward: -382 Explore: 0.00
Episode: 123  Reward: -269 Explore: 0.00
Episode: 124  Reward: -268 Explore: 0.00
Episode: 125  Reward: -274 Explore: 0.00
Episode: 126  Reward: -140 Explore: 0.00
Episode: 127  Reward: -407 Explore: 0.00
Episode: 128  Reward: -5 Explore: 0.00
Episode: 129  Reward: -7 Explore: 0.00
Episode: 130  Reward: -6 Explore: 0.00
Episode: 131  Reward: -402 Explore: 0.00
Episode: 132  Reward: -279 Explore: 0.00
Episode: 133  Reward: -138 Explore: 0.00
Episode: 134  Reward: -416 Explore: 0.00
Episode: 135  Reward: -140 Explore: 0.00
Episode: 136  Reward: -870 Explore: 0.00
Episode: 137  Reward: -274 Explore: 0.00
Episode: 138  Reward: -415 Explore: 0.00
Episode: 139  Reward: -384 Explore: 0.00
Episode: 140  Reward: -270 Explore: 0.00
Episode: 141  Reward: -417 Explore: 0.00
Episode: 142  Reward: -138 Explore: 0.00
Episode: 143  Reward: -136 Explore: 0.00
Episode: 144  Reward: -134 Explore: 0.00
Episode: 145  Reward: -272 Explore: 0.00
Episode: 146  Reward: -385 Explore: 0.00
Episode: 147  Reward: -134 Explore: 0.00
Episode: 148  Reward: -1050 Explore: 0.00
Episode: 149  Reward: -395 Explore: 0.00
Episode: 150  Reward: -272 Explore: 0.00
Episode: 151  Reward: -383 Explore: 0.00
Episode: 152  Reward: -415 Explore: 0.00
Episode: 153  Reward: -4 Explore: 0.00
Episode: 154  Reward: -394 Explore: 0.00
Episode: 155  Reward: -137 Explore: 0.00
Episode: 156  Reward: -398 Explore: 0.00
Episode: 157  Reward: -495 Explore: 0.00
Episode: 158  Reward: -142 Explore: 0.00
Episode: 159  Reward: -598 Explore: 0.00
Episode: 160  Reward: -143 Explore: 0.00
Episode: 161  Reward: -296 Explore: 0.00
Episode: 162  Reward: -137 Explore: 0.00
Episode: 163  Reward: -137 Explore: 0.00
Episode: 164  Reward: -138 Explore: 0.00
Episode: 165  Reward: -267 Explore: 0.00
Episode: 166  Reward: -420 Explore: 0.00
Episode: 167  Reward: -268 Explore: 0.00
Episode: 168  Reward: -428 Explore: 0.00
Episode: 169  Reward: -137 Explore: 0.00
Episode: 170  Reward: -299 Explore: 0.00
Episode: 171  Reward: -470 Explore: 0.00
Episode: 172  Reward: -137 Explore: 0.00
Episode: 173  Reward: -267 Explore: 0.00
Episode: 174  Reward: -267 Explore: 0.00
Episode: 175  Reward: -136 Explore: 0.00
Episode: 176  Reward: -147 Explore: 0.00
Episode: 177  Reward: -421 Explore: 0.00
Episode: 178  Reward: -405 Explore: 0.00
Episode: 179  Reward: -139 Explore: 0.00
Episode: 180  Reward: -133 Explore: 0.00
Episode: 181  Reward: -292 Explore: 0.00
Episode: 182  Reward: -131 Explore: 0.00
Episode: 183  Reward: -258 Explore: 0.00
Episode: 184  Reward: -694 Explore: 0.00
Episode: 185  Reward: -138 Explore: 0.00
Episode: 186  Reward: -132 Explore: 0.00
Episode: 187  Reward: -135 Explore: 0.00
Episode: 188  Reward: -263 Explore: 0.00
Episode: 189  Reward: -266 Explore: 0.00
Episode: 190  Reward: -1352 Explore: 0.00
Episode: 191  Reward: -374 Explore: 0.00
Episode: 192  Reward: -134 Explore: 0.00
Episode: 193  Reward: -397 Explore: 0.00
Episode: 194  Reward: -546 Explore: 0.00
Episode: 195  Reward: -282 Explore: 0.00
Episode: 196  Reward: -264 Explore: 0.00
Episode: 197  Reward: -252 Explore: 0.00
Episode: 198  Reward: -390 Explore: 0.00
Episode: 199  Reward: -391 Explore: 0.00
Running time:  114.84853196144104

结论

训练效果上，3>2>1

方小汪
关注
  • 0
    点赞
  • 踩
  • 5
    收藏
    觉得还不错? 一键收藏
  • 0
    评论
专栏目录
莫烦python tensorflow代码
07-18
看莫烦python网课的时候发现github上的代码与所讲代码并不对应，于是跟着视频自己敲的，亲测可用
莫烦 Python 教程 2017.5.10
05-10
莫烦 Python 教程 2017.5.10
eslint-plugin-only-warn:将错误降级为警告
05-01
eslint-plugin-only-warn 将错误降级为警告 安装 您首先需要安装 ： $ npm i eslint --save-dev 接下来，安装eslint-plugin-only-warn ： $ npm install eslint-plugin-only-warn --save-dev 注意：如果全局安装了ESLint（使用-g标志），则还必须全局安装eslint-plugin-only-warn 。 用法 将“ only-warn添加到.eslintrc配置文件的“插件”部分。 您可以省略eslint-plugin-前缀： { " plugins " : [ " only-warn " ] }
PythonSuperMario:python编写的SuperMarioBros游戏（支持1-1至1-4级）
05-10
超级马里奥 基于改进的supermario游戏。 支持四个级别：1-1至1-4级 支持进入管道 使用json文件存储关卡数据（例如敌人，砖块，盒子和管道的位置） 在1-3和1-4级中添加新敌人 在1-2级添加滑块 要求 Python 3.7 Python-Pygame 1.9 如何开始游戏 $ python main.py 怎么玩 使用LEFT / RIGHT / DOWN键控制播放器 使用键“ a”跳转 使用键's'射击防火墙或运行 演示版
运行.py文件与运行.sh文件出现同样的bug
weixin_40945354的博客
08-08 599
python dqn_family.py /usr/local/lib/python3.6/dist-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow')) INFO - 2020-08-08 05:48:47,724 - [__ma
好像不是这么运行的，步骤是错的
weixin_40945354的博客
08-08 893
sh rainbow.sh /usr/local/lib/python3.6/dist-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow')) INFO - 2020-08-08 05:30:33,963 - [__main__ ma
bug：ImportError: cannot import name ‘PrioritizedBuffer‘ from ‘chainerrl.replay_buffer‘
weixin_40945354的博客
08-05 502
python train_dqfd.py /Users/ixxx/opt/anaconda3/lib/python3.7/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize('%s: %s'%('WARN', msg % args), 'yellow')) Traceback (most recent cal.
这报的是什么错，没见过
weixin_40945354的博客
08-04 1127
(base) bogon:competition_submission_template $ python train.py /Users/ /opt/anaconda3/lib/python3.7/site-packages/gym/logger.py:30: UserWarning: WARN: Box bound precision lowered by casting to float32 warnings.warn(colorize('%s: %s'%('WARN', msg % args),
DDPG算法实现（python完整代码）
weixin_42898871的博客
02-06 2340
DDPG算法实现，python完整代码及详解
莫烦python,tensorflow
11-09
本文的内容为视频莫烦python的配套代码，视频可以在优酷或者youtube上观看，视屏是短视频，每个视频10分钟以内，很好的初学者材料。还有tensorflow示例
莫烦python RL代码
08-27
该文件为莫烦python网课中reinforcement learning部分的代码
sklearn_msgpack:Scikit使用MsgPack学习模型持久性
05-16
Scikit通过MsgPack学习模型持久性 介绍 Scikit学习在训练后使用来存储模型 这种方法存在已知 安全性-泡菜包含字节码 可维护性-需要相同版本的sklearn 慢-因为它不仅包含经过训练的权重而包含字节码 UserWarning: Trying to unpickle estimator MLPClassifier from version 0.18 when using version 0.19.1. This might lead to breaking code or invalid results. Use at your own risk. 我们的方法 为了持久化模型实例，我们构造了一个包含以下内容的字典 用于构造实例的关键字参数 可训练参数的值（例如权重） 其他所需的实例属性 我们使用来存储此字典 受支持的课程 添加更多非常容易 表现 我们已经看到MLPC
莫烦PYTHON——Python3基础教程 学习心得（2）
12-21
莫烦PYTHON——Python3基础教程 学习心得（2）5 定义功能5.1 def函数5.2 函数参数5.3 函数默认参数6 变量形式6.1 全局&局部变量7 模块安装7.1 模块安装8 文件读取8.1 读写文件18.2 读写文件28.3 读写文件3 5 定义功能 5.1 def函数 新建Python文件，输入 def function(): print('This is a function') a = 1 + 2 print(a) function() 得到 This is a function 3 5.2 函数参数 新建Python文件，输入 def fun
python中np.clip()的用法
热门推荐
方小汪的博客
02-01 1万+
主要参考python中numpy模块下的np.clip()的用法,稍有改动 Numpy 中clip函数的使用 numpy.clip(a, a_min, a_max, out=None) Clip (limit) the values in an array. Given an interval, values outside the interval are clipped to the inte...
python中的reshape
方小汪的博客
01-31 1万+
小有改动,主要参考: python：shape和reshape()函数 python中reshape 在numpy中，shape和reshape()函数的功能都是对于数组的形状进行操作。shape函数可以了解数组的结构,reshape()函数可以对数组的结构进行改变。 shape import numpy as np #设置一个数组 a = np.array([1,2,3,4,5,6,7,8]) ...
查看tensorflow和tensorboard版本
方小汪的博客
09-01 5767
前面采取conda的方式安装tensorflow等 1、在虚拟环境py27中conda安装Tensorflow conda install tensorflow-gpu==1.8.0 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/pkgs/main 2、在虚拟环境py27中conda安装cuda conda install cudatoolkit=9.0 -c https://mirrors.tuna.tsinghua.edu.cn/anaconda/p
解决logging的保存路径问题
方小汪的博客
08-31 4067
基本参照链接中的2.2来修改代码 先添加 import logging import os modelPath = os.path.dirname(os.path.realpath(__file__)) 然后将 logger = logging.getLogger(__name__) logger.setLevel(level = logging.INFO) handler = logging.FileHandler("log.txt") handler.setLevel(logging.INFO) fo
Math.hypot()
方小汪的博客
01-18 3149
Math.hypot() 函数返回它的所有参数的平方和的平方根，即： \mathtt{\operatorname{Math.hypot}(v_1, v_2, \dots, v_n)} = \sqrt{\sum_{i=1}^n v_i^2} = \sqrt{v_1^2 + v_2^2 + \dots + v_n^2} 具体详见Math.hypot()，讲得很好很清楚。 ...
莫烦python 强化学习 例程
最新发布
09-29
莫烦Python的强化学习例程是一个基于Q-learning算法的探宝者游戏。该例程使用了numpy和pandas库，并设置了一些超参数，如贪婪度、学习率和奖励递减值。Q-table用于存储每个状态的动作值，并通过贪婪模式和探索模式选择动作。环境更新部分可视化探宝者在环境中的位置，并根据奖励规则进行状态转换和奖励计算。

“相关推荐”对你有帮助么？

  • 非常没帮助
  • 没帮助
  • 一般
  • 有帮助
  • 非常有帮助
提交
评论
添加红包

请填写红包祝福语或标题

个

红包个数最小为10个

元

红包金额最低5元

当前余额3.43元 前往充值 >
需支付：10.00元
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付元
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明：

1.余额是钱包充值的虚拟货币，按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载，可以购买VIP、付费专栏及课程。

余额充值