📝 update the result of sycamore-n53 m12, m14, m16, m20

result: 以下的结果都需要+log10(2) ，可以参考以下讨论：
https://github.com/AI4Finance-Foundation/ElegantRL_Solver/issues/102#issuecomment-1508268430

|sycamore | Result1| Result2 | NumSamples | UsedTime
|-------|-------|-------|-------|-------|
| n53 m12 | 15.478 | 16.449 | 185856 | 56930 |
| n53 m14 | 16.610 | 17.748 | 173568 | 54152 |
| n53 m16 | 22.014 | 32.511 | 153088 | 52947 |
| n53 m18 | | | | |
| n53 m20 | 21.782 | 22.585 | 148992 | 58058 |

## sycamore n53 m12
```
228 22.789 2.196e+01 TimeUsed 54169
232 24.986 2.228e+01 TimeUsed 55085
236 25.889 2.051e+01 TimeUsed 56010
240 20.804 1.967e+01 TimeUsed 56930
| buffer.save_or_load_history(): Save ./task_TNCO_00/replay_buffer_states.pth torch.Size([185856, 414])
| buffer.save_or_load_history(): Save ./task_TNCO_00/replay_buffer_scores.pth torch.Size([185856, 1])

min_score: 15.478
avg_score: 24.392 ± 4.663
max_score: 49.068
best_result:
tensor([235, 371, 215, 137, 246, 62, 320, 178, 147, 325, 31, 17, 274, 333,
234, 389, 142, 49, 311, 351, 271, 218, 89, 121, 96, 401, 25, 230,
8, 369, 350, 257, 318, 248, 229, 236, 52, 14, 292, 139, 383, 343,
207, 195, 209, 47, 394, 355, 329, 149, 53, 130, 372, 398, 273, 339,
278, 314, 298, 28, 206, 98, 384, 74, 217, 256, 65, 134, 354, 323,
167, 166, 390, 151, 190, 182, 382, 367, 128, 18, 10, 408, 321, 119,
344, 100, 199, 120, 181, 405, 179, 288, 411, 140, 330, 305, 264, 336,
208, 356, 168, 60, 266, 348, 242, 59, 268, 397, 214, 243, 143, 263,
270, 87, 388, 125, 29, 204, 5, 16, 191, 282, 118, 322, 81, 104,
211, 228, 34, 296, 76, 152, 114, 392, 406, 24, 171, 244, 116, 306,
359, 138, 362, 338, 290, 227, 12, 308, 172, 237, 379, 197, 254, 259,
146, 176, 252, 366, 332, 22, 43, 216, 99, 79, 275, 196, 67, 258,
342, 294, 373, 198, 56, 283, 108, 346, 64, 175, 88, 102, 27, 135,
123, 357, 324, 19, 7, 55, 319, 162, 9, 349, 193, 41, 192, 155,
412, 352, 72, 186, 69, 160, 386, 267, 150, 312, 205, 20, 309, 364,
272, 164, 82, 23, 33, 358, 68, 107, 345, 285, 226, 95, 85, 145,
284, 94, 38, 233, 180, 378, 2, 42, 303, 300, 387, 360, 327, 91,
32, 109, 240, 260, 287, 115, 184, 86, 249, 21, 203, 75, 78, 341,
317, 286, 1, 276, 253, 131, 251, 241, 328, 36, 315, 310, 110, 11,
245, 37, 377, 381, 40, 307, 297, 4, 158, 289, 83, 188, 111, 293,
337, 396, 361, 280, 50, 380, 368, 84, 51, 54, 340, 212, 370, 169,
154, 326, 385, 255, 44, 201, 232, 103, 353, 409, 262, 156, 291, 101,
250, 200, 247, 80, 105, 194, 113, 157, 402, 265, 159, 174, 57, 133,
141, 185, 58, 238, 106, 334, 129, 136, 313, 127, 3, 365, 61, 277,
73, 92, 391, 46, 71, 213, 231, 26, 399, 144, 210, 304, 375, 374,
148, 269, 331, 30, 13, 410, 363, 165, 400, 316, 124, 222, 93, 153,
117, 39, 70, 170, 6, 132, 77, 224, 66, 63, 48, 239, 413, 302,
376, 219, 45, 126, 173, 221, 223, 183, 404, 177, 97, 279, 187, 407,
189, 15, 281, 395, 393, 403, 301, 112, 35, 90, 295, 225, 299, 0,
163, 261, 220, 122, 202, 161, 335, 347], device='cuda:0')
```
---

```
180 18.700 1.616e+01 TimeUsed 48409
184 19.871 1.838e+01 TimeUsed 49428
188 21.397 1.973e+01 TimeUsed 50447
192 24.096 1.993e+01 TimeUsed 51460
| buffer.save_or_load_history(): Save ./task_TNCO_04/replay_buffer_states.pth torch.Size([165376, 414])
| buffer.save_or_load_history(): Save ./task_TNCO_04/replay_buffer_scores.pth torch.Size([165376, 1])

min_score: 16.449
avg_score: 25.135 ± 5.301
max_score: 49.670
best_result:
tensor([396, 88, 166, 366, 408, 81, 167, 51, 243, 238, 148, 90, 5, 222,
159, 305, 361, 198, 22, 295, 321, 128, 339, 310, 169, 219, 375, 224,
409, 372, 38, 241, 247, 146, 338, 200, 36, 52, 54, 178, 226, 234,
173, 192, 117, 260, 108, 278, 387, 147, 245, 399, 227, 275, 1, 329,
411, 140, 341, 152, 55, 132, 17, 312, 168, 297, 92, 385, 345, 237,
119, 120, 102, 101, 44, 75, 94, 89, 332, 307, 74, 85, 212, 181,
118, 348, 23, 412, 413, 69, 196, 386, 235, 43, 383, 45, 210, 172,
286, 223, 256, 144, 183, 322, 253, 80, 261, 407, 291, 113, 301, 343,
353, 216, 115, 378, 134, 158, 86, 73, 404, 35, 66, 106, 251, 136,
161, 137, 274, 246, 8, 162, 97, 32, 157, 18, 91, 303, 410, 349,
290, 177, 53, 397, 111, 373, 127, 105, 28, 201, 84, 104, 125, 346,
323, 49, 347, 271, 304, 355, 208, 309, 124, 37, 344, 306, 360, 389,
31, 377, 392, 30, 39, 284, 163, 351, 10, 255, 395, 186, 382, 184,
82, 126, 130, 330, 142, 264, 342, 296, 123, 250, 20, 257, 313, 46,
268, 34, 289, 170, 308, 380, 150, 265, 371, 213, 93, 154, 333, 262,
61, 151, 232, 87, 56, 285, 206, 267, 263, 340, 217, 114, 317, 107,
63, 390, 121, 139, 6, 194, 225, 336, 242, 112, 320, 356, 248, 391,
283, 379, 29, 83, 64, 281, 292, 135, 42, 276, 324, 33, 402, 103,
204, 314, 156, 193, 364, 68, 244, 352, 110, 369, 187, 272, 214, 365,
252, 393, 359, 211, 164, 368, 400, 195, 40, 116, 279, 205, 259, 337,
319, 199, 7, 240, 77, 72, 370, 209, 145, 122, 207, 60, 405, 327,
160, 21, 273, 62, 334, 406, 100, 14, 197, 26, 311, 403, 16, 354,
129, 269, 71, 109, 315, 374, 203, 266, 220, 335, 175, 230, 302, 202,
19, 376, 153, 174, 328, 388, 188, 96, 138, 98, 287, 25, 326, 190,
191, 239, 288, 76, 50, 179, 299, 48, 3, 78, 11, 228, 280, 57,
215, 282, 2, 398, 149, 15, 47, 182, 300, 79, 236, 12, 249, 233,
131, 218, 362, 363, 58, 67, 357, 155, 0, 41, 24, 270, 293, 325,
229, 133, 9, 13, 277, 4, 298, 254, 65, 171, 358, 350, 180, 185,
316, 367, 221, 331, 143, 59, 258, 394, 165, 176, 401, 318, 189, 70,
27, 381, 231, 294, 141, 384, 95, 99], device='cuda:4')
```