hot update A2C

This commit is contained in:
johnjim0816
2022-08-29 15:12:33 +08:00
parent 99a3c1afec
commit 0b0f7e857d
109 changed files with 8213 additions and 1658 deletions

View File

@@ -1 +0,0 @@
{"algo_name": "Sarsa", "env_name": "CliffWalking-v0", "train_eps": 300, "test_eps": 20, "ep_max_steps": 200, "gamma": 0.99, "epsilon_start": 0.9, "epsilon_end": 0.01, "epsilon_decay": 200, "lr": 0.2, "device": "cpu", "result_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220803-142740/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220803-142740/models/", "save_fig": true}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 34 KiB

Binary file not shown.

Before

Width:  |  Height:  |  Size: 54 KiB

View File

@@ -1,15 +0,0 @@
{
"algo_name": "Sarsa",
"env_name": "CliffWalking-v0",
"train_eps": 400,
"test_eps": 20,
"gamma": 0.9,
"epsilon_start": 0.95,
"epsilon_end": 0.01,
"epsilon_decay": 300,
"lr": 0.1,
"device": "cpu",
"result_path": "c:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\Sarsa/outputs/CliffWalking-v0/20220804-223029/results/",
"model_path": "c:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\Sarsa/outputs/CliffWalking-v0/20220804-223029/models/",
"save_fig": true
}

Binary file not shown.

Before

Width:  |  Height:  |  Size: 34 KiB

View File

@@ -0,0 +1,19 @@
{
"algo_name": "Sarsa",
"env_name": "CliffWalking-v0",
"train_eps": 400,
"test_eps": 20,
"gamma": 0.9,
"epsilon_start": 0.95,
"epsilon_end": 0.01,
"epsilon_decay": 300,
"lr": 0.1,
"device": "cpu",
"seed": 10,
"show_fig": false,
"save_fig": true,
"result_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/results/",
"model_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/models/",
"n_states": 48,
"n_actions": 4
}

View File

@@ -0,0 +1,21 @@
episodes,rewards,steps
0,-15,15
1,-15,15
2,-15,15
3,-15,15
4,-15,15
5,-15,15
6,-15,15
7,-15,15
8,-15,15
9,-15,15
10,-15,15
11,-15,15
12,-15,15
13,-15,15
14,-15,15
15,-15,15
16,-15,15
17,-15,15
18,-15,15
19,-15,15
1 episodes rewards steps
2 0 -15 15
3 1 -15 15
4 2 -15 15
5 3 -15 15
6 4 -15 15
7 5 -15 15
8 6 -15 15
9 7 -15 15
10 8 -15 15
11 9 -15 15
12 10 -15 15
13 11 -15 15
14 12 -15 15
15 13 -15 15
16 14 -15 15
17 15 -15 15
18 16 -15 15
19 17 -15 15
20 18 -15 15
21 19 -15 15

Binary file not shown.

After

Width:  |  Height:  |  Size: 33 KiB

View File

@@ -0,0 +1,401 @@
episodes,rewards,steps
0,-649,154
1,-2822,842
2,-176,176
3,-139,139
4,-221,221
5,-51,51
6,-219,219
7,-247,148
8,-90,90
9,-145,145
10,-104,104
11,-162,162
12,-49,49
13,-129,129
14,-140,140
15,-19,19
16,-131,131
17,-115,115
18,-43,43
19,-133,133
20,-73,73
21,-89,89
22,-131,131
23,-61,61
24,-113,113
25,-119,119
26,-119,119
27,-71,71
28,-132,132
29,-47,47
30,-79,79
31,-57,57
32,-125,125
33,-77,77
34,-87,87
35,-49,49
36,-57,57
37,-81,81
38,-81,81
39,-97,97
40,-61,61
41,-85,85
42,-217,118
43,-39,39
44,-117,117
45,-41,41
46,-71,71
47,-105,105
48,-73,73
49,-68,68
50,-95,95
51,-41,41
52,-41,41
53,-67,67
54,-71,71
55,-65,65
56,-41,41
57,-61,61
58,-81,81
59,-21,21
60,-76,76
61,-80,80
62,-23,23
63,-53,53
64,-67,67
65,-33,33
66,-41,41
67,-59,59
68,-33,33
69,-64,64
70,-188,89
71,-47,47
72,-57,57
73,-45,45
74,-33,33
75,-79,79
76,-45,45
77,-23,23
78,-47,47
79,-57,57
80,-47,47
81,-45,45
82,-53,53
83,-29,29
84,-33,33
85,-69,69
86,-61,61
87,-35,35
88,-59,59
89,-43,43
90,-17,17
91,-39,39
92,-59,59
93,-29,29
94,-31,31
95,-55,55
96,-35,35
97,-45,45
98,-29,29
99,-59,59
100,-25,25
101,-29,29
102,-33,33
103,-39,39
104,-19,19
105,-47,47
106,-57,57
107,-19,19
108,-47,47
109,-25,25
110,-23,23
111,-53,53
112,-39,39
113,-34,34
114,-27,27
115,-27,27
116,-63,63
117,-33,33
118,-17,17
119,-21,21
120,-19,19
121,-49,49
122,-25,25
123,-39,39
124,-25,25
125,-167,68
126,-35,35
127,-29,29
128,-31,31
129,-44,44
130,-33,33
131,-23,23
132,-37,37
133,-134,35
134,-31,31
135,-19,19
136,-29,29
137,-37,37
138,-25,25
139,-39,39
140,-47,47
141,-29,29
142,-27,27
143,-21,21
144,-41,41
145,-29,29
146,-25,25
147,-25,25
148,-21,21
149,-29,29
150,-39,39
151,-35,35
152,-35,35
153,-32,32
154,-31,31
155,-19,19
156,-21,21
157,-35,35
158,-33,33
159,-37,37
160,-25,25
161,-41,41
162,-25,25
163,-23,23
164,-27,27
165,-25,25
166,-39,39
167,-28,28
168,-24,24
169,-23,23
170,-41,41
171,-17,17
172,-35,35
173,-23,23
174,-29,29
175,-17,17
176,-39,39
177,-33,33
178,-29,29
179,-24,24
180,-23,23
181,-19,19
182,-15,15
183,-23,23
184,-39,39
185,-25,25
186,-35,35
187,-33,33
188,-19,19
189,-35,35
190,-21,21
191,-131,32
192,-15,15
193,-23,23
194,-21,21
195,-17,17
196,-23,23
197,-31,31
198,-21,21
199,-31,31
200,-35,35
201,-27,27
202,-19,19
203,-21,21
204,-23,23
205,-23,23
206,-21,21
207,-31,31
208,-25,25
209,-23,23
210,-17,17
211,-19,19
212,-25,25
213,-23,23
214,-19,19
215,-19,19
216,-25,25
217,-25,25
218,-25,25
219,-25,25
220,-23,23
221,-19,19
222,-19,19
223,-149,50
224,-41,41
225,-19,19
226,-29,29
227,-37,37
228,-17,17
229,-17,17
230,-19,19
231,-27,27
232,-19,19
233,-33,33
234,-23,23
235,-23,23
236,-34,34
237,-15,15
238,-33,33
239,-29,29
240,-17,17
241,-23,23
242,-17,17
243,-19,19
244,-21,21
245,-23,23
246,-17,17
247,-15,15
248,-39,39
249,-21,21
250,-23,23
251,-29,29
252,-15,15
253,-17,17
254,-29,29
255,-15,15
256,-21,21
257,-19,19
258,-19,19
259,-21,21
260,-17,17
261,-21,21
262,-27,27
263,-27,27
264,-21,21
265,-19,19
266,-17,17
267,-23,23
268,-19,19
269,-17,17
270,-19,19
271,-19,19
272,-17,17
273,-23,23
274,-17,17
275,-22,22
276,-31,31
277,-19,19
278,-17,17
279,-33,33
280,-19,19
281,-17,17
282,-31,31
283,-15,15
284,-15,15
285,-15,15
286,-29,29
287,-19,19
288,-17,17
289,-26,26
290,-17,17
291,-19,19
292,-15,15
293,-21,21
294,-21,21
295,-15,15
296,-19,19
297,-15,15
298,-17,17
299,-19,19
300,-17,17
301,-21,21
302,-17,17
303,-27,27
304,-17,17
305,-19,19
306,-15,15
307,-19,19
308,-33,33
309,-17,17
310,-20,20
311,-19,19
312,-17,17
313,-15,15
314,-23,23
315,-15,15
316,-15,15
317,-17,17
318,-25,25
319,-15,15
320,-17,17
321,-19,19
322,-17,17
323,-15,15
324,-23,23
325,-19,19
326,-17,17
327,-23,23
328,-15,15
329,-19,19
330,-15,15
331,-17,17
332,-19,19
333,-15,15
334,-17,17
335,-17,17
336,-19,19
337,-15,15
338,-19,19
339,-19,19
340,-17,17
341,-15,15
342,-21,21
343,-19,19
344,-17,17
345,-17,17
346,-15,15
347,-21,21
348,-20,20
349,-15,15
350,-15,15
351,-15,15
352,-19,19
353,-17,17
354,-15,15
355,-27,27
356,-15,15
357,-15,15
358,-23,23
359,-125,26
360,-132,33
361,-17,17
362,-15,15
363,-17,17
364,-23,23
365,-17,17
366,-15,15
367,-15,15
368,-17,17
369,-15,15
370,-17,17
371,-15,15
372,-15,15
373,-15,15
374,-15,15
375,-15,15
376,-15,15
377,-15,15
378,-15,15
379,-15,15
380,-17,17
381,-15,15
382,-15,15
383,-19,19
384,-15,15
385,-17,17
386,-27,27
387,-15,15
388,-21,21
389,-125,26
390,-15,15
391,-15,15
392,-15,15
393,-27,27
394,-15,15
395,-15,15
396,-17,17
397,-15,15
398,-15,15
399,-15,15
1 episodes rewards steps
2 0 -649 154
3 1 -2822 842
4 2 -176 176
5 3 -139 139
6 4 -221 221
7 5 -51 51
8 6 -219 219
9 7 -247 148
10 8 -90 90
11 9 -145 145
12 10 -104 104
13 11 -162 162
14 12 -49 49
15 13 -129 129
16 14 -140 140
17 15 -19 19
18 16 -131 131
19 17 -115 115
20 18 -43 43
21 19 -133 133
22 20 -73 73
23 21 -89 89
24 22 -131 131
25 23 -61 61
26 24 -113 113
27 25 -119 119
28 26 -119 119
29 27 -71 71
30 28 -132 132
31 29 -47 47
32 30 -79 79
33 31 -57 57
34 32 -125 125
35 33 -77 77
36 34 -87 87
37 35 -49 49
38 36 -57 57
39 37 -81 81
40 38 -81 81
41 39 -97 97
42 40 -61 61
43 41 -85 85
44 42 -217 118
45 43 -39 39
46 44 -117 117
47 45 -41 41
48 46 -71 71
49 47 -105 105
50 48 -73 73
51 49 -68 68
52 50 -95 95
53 51 -41 41
54 52 -41 41
55 53 -67 67
56 54 -71 71
57 55 -65 65
58 56 -41 41
59 57 -61 61
60 58 -81 81
61 59 -21 21
62 60 -76 76
63 61 -80 80
64 62 -23 23
65 63 -53 53
66 64 -67 67
67 65 -33 33
68 66 -41 41
69 67 -59 59
70 68 -33 33
71 69 -64 64
72 70 -188 89
73 71 -47 47
74 72 -57 57
75 73 -45 45
76 74 -33 33
77 75 -79 79
78 76 -45 45
79 77 -23 23
80 78 -47 47
81 79 -57 57
82 80 -47 47
83 81 -45 45
84 82 -53 53
85 83 -29 29
86 84 -33 33
87 85 -69 69
88 86 -61 61
89 87 -35 35
90 88 -59 59
91 89 -43 43
92 90 -17 17
93 91 -39 39
94 92 -59 59
95 93 -29 29
96 94 -31 31
97 95 -55 55
98 96 -35 35
99 97 -45 45
100 98 -29 29
101 99 -59 59
102 100 -25 25
103 101 -29 29
104 102 -33 33
105 103 -39 39
106 104 -19 19
107 105 -47 47
108 106 -57 57
109 107 -19 19
110 108 -47 47
111 109 -25 25
112 110 -23 23
113 111 -53 53
114 112 -39 39
115 113 -34 34
116 114 -27 27
117 115 -27 27
118 116 -63 63
119 117 -33 33
120 118 -17 17
121 119 -21 21
122 120 -19 19
123 121 -49 49
124 122 -25 25
125 123 -39 39
126 124 -25 25
127 125 -167 68
128 126 -35 35
129 127 -29 29
130 128 -31 31
131 129 -44 44
132 130 -33 33
133 131 -23 23
134 132 -37 37
135 133 -134 35
136 134 -31 31
137 135 -19 19
138 136 -29 29
139 137 -37 37
140 138 -25 25
141 139 -39 39
142 140 -47 47
143 141 -29 29
144 142 -27 27
145 143 -21 21
146 144 -41 41
147 145 -29 29
148 146 -25 25
149 147 -25 25
150 148 -21 21
151 149 -29 29
152 150 -39 39
153 151 -35 35
154 152 -35 35
155 153 -32 32
156 154 -31 31
157 155 -19 19
158 156 -21 21
159 157 -35 35
160 158 -33 33
161 159 -37 37
162 160 -25 25
163 161 -41 41
164 162 -25 25
165 163 -23 23
166 164 -27 27
167 165 -25 25
168 166 -39 39
169 167 -28 28
170 168 -24 24
171 169 -23 23
172 170 -41 41
173 171 -17 17
174 172 -35 35
175 173 -23 23
176 174 -29 29
177 175 -17 17
178 176 -39 39
179 177 -33 33
180 178 -29 29
181 179 -24 24
182 180 -23 23
183 181 -19 19
184 182 -15 15
185 183 -23 23
186 184 -39 39
187 185 -25 25
188 186 -35 35
189 187 -33 33
190 188 -19 19
191 189 -35 35
192 190 -21 21
193 191 -131 32
194 192 -15 15
195 193 -23 23
196 194 -21 21
197 195 -17 17
198 196 -23 23
199 197 -31 31
200 198 -21 21
201 199 -31 31
202 200 -35 35
203 201 -27 27
204 202 -19 19
205 203 -21 21
206 204 -23 23
207 205 -23 23
208 206 -21 21
209 207 -31 31
210 208 -25 25
211 209 -23 23
212 210 -17 17
213 211 -19 19
214 212 -25 25
215 213 -23 23
216 214 -19 19
217 215 -19 19
218 216 -25 25
219 217 -25 25
220 218 -25 25
221 219 -25 25
222 220 -23 23
223 221 -19 19
224 222 -19 19
225 223 -149 50
226 224 -41 41
227 225 -19 19
228 226 -29 29
229 227 -37 37
230 228 -17 17
231 229 -17 17
232 230 -19 19
233 231 -27 27
234 232 -19 19
235 233 -33 33
236 234 -23 23
237 235 -23 23
238 236 -34 34
239 237 -15 15
240 238 -33 33
241 239 -29 29
242 240 -17 17
243 241 -23 23
244 242 -17 17
245 243 -19 19
246 244 -21 21
247 245 -23 23
248 246 -17 17
249 247 -15 15
250 248 -39 39
251 249 -21 21
252 250 -23 23
253 251 -29 29
254 252 -15 15
255 253 -17 17
256 254 -29 29
257 255 -15 15
258 256 -21 21
259 257 -19 19
260 258 -19 19
261 259 -21 21
262 260 -17 17
263 261 -21 21
264 262 -27 27
265 263 -27 27
266 264 -21 21
267 265 -19 19
268 266 -17 17
269 267 -23 23
270 268 -19 19
271 269 -17 17
272 270 -19 19
273 271 -19 19
274 272 -17 17
275 273 -23 23
276 274 -17 17
277 275 -22 22
278 276 -31 31
279 277 -19 19
280 278 -17 17
281 279 -33 33
282 280 -19 19
283 281 -17 17
284 282 -31 31
285 283 -15 15
286 284 -15 15
287 285 -15 15
288 286 -29 29
289 287 -19 19
290 288 -17 17
291 289 -26 26
292 290 -17 17
293 291 -19 19
294 292 -15 15
295 293 -21 21
296 294 -21 21
297 295 -15 15
298 296 -19 19
299 297 -15 15
300 298 -17 17
301 299 -19 19
302 300 -17 17
303 301 -21 21
304 302 -17 17
305 303 -27 27
306 304 -17 17
307 305 -19 19
308 306 -15 15
309 307 -19 19
310 308 -33 33
311 309 -17 17
312 310 -20 20
313 311 -19 19
314 312 -17 17
315 313 -15 15
316 314 -23 23
317 315 -15 15
318 316 -15 15
319 317 -17 17
320 318 -25 25
321 319 -15 15
322 320 -17 17
323 321 -19 19
324 322 -17 17
325 323 -15 15
326 324 -23 23
327 325 -19 19
328 326 -17 17
329 327 -23 23
330 328 -15 15
331 329 -19 19
332 330 -15 15
333 331 -17 17
334 332 -19 19
335 333 -15 15
336 334 -17 17
337 335 -17 17
338 336 -19 19
339 337 -15 15
340 338 -19 19
341 339 -19 19
342 340 -17 17
343 341 -15 15
344 342 -21 21
345 343 -19 19
346 344 -17 17
347 345 -17 17
348 346 -15 15
349 347 -21 21
350 348 -20 20
351 349 -15 15
352 350 -15 15
353 351 -15 15
354 352 -19 19
355 353 -17 17
356 354 -15 15
357 355 -27 27
358 356 -15 15
359 357 -15 15
360 358 -23 23
361 359 -125 26
362 360 -132 33
363 361 -17 17
364 362 -15 15
365 363 -17 17
366 364 -23 23
367 365 -17 17
368 366 -15 15
369 367 -15 15
370 368 -17 17
371 369 -15 15
372 370 -17 17
373 371 -15 15
374 372 -15 15
375 373 -15 15
376 374 -15 15
377 375 -15 15
378 376 -15 15
379 377 -15 15
380 378 -15 15
381 379 -15 15
382 380 -17 17
383 381 -15 15
384 382 -15 15
385 383 -19 19
386 384 -15 15
387 385 -17 17
388 386 -27 27
389 387 -15 15
390 388 -21 21
391 389 -125 26
392 390 -15 15
393 391 -15 15
394 392 -15 15
395 393 -27 27
396 394 -15 15
397 395 -15 15
398 396 -17 17
399 397 -15 15
400 398 -15 15
401 399 -15 15