hot update A2C
This commit is contained in:
@@ -5,7 +5,7 @@ Author: John
|
||||
Email: johnjim0816@gmail.com
|
||||
Date: 2020-09-11 23:03:00
|
||||
LastEditor: John
|
||||
LastEditTime: 2022-08-25 14:59:15
|
||||
LastEditTime: 2022-08-26 22:46:21
|
||||
Discription:
|
||||
Environment:
|
||||
'''
|
||||
@@ -57,7 +57,10 @@ class Main(Launcher):
|
||||
env = CliffWalkingWapper(env)
|
||||
if cfg['seed'] !=0: # set random seed
|
||||
all_seed(env,seed=cfg["seed"])
|
||||
n_states = env.observation_space.n # state dimension
|
||||
try: # state dimension
|
||||
n_states = env.observation_space.n # print(hasattr(env.observation_space, 'n'))
|
||||
except AttributeError:
|
||||
n_states = env.observation_space.shape[0] # print(hasattr(env.observation_space, 'shape'))
|
||||
n_actions = env.action_space.n # action dimension
|
||||
print(f"n_states: {n_states}, n_actions: {n_actions}")
|
||||
cfg.update({"n_states":n_states,"n_actions":n_actions}) # update to cfg paramters
|
||||
|
||||
@@ -1,19 +0,0 @@
|
||||
{
|
||||
"algo_name": "Q-learning",
|
||||
"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/QLearning/outputs/CliffWalking-v0/20220824-103255/results/",
|
||||
"model_path": "/Users/jj/Desktop/rl-tutorials/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/models/",
|
||||
"n_states": 48,
|
||||
"n_actions": 4
|
||||
}
|
||||
@@ -1,21 +0,0 @@
|
||||
episodes,rewards
|
||||
0,-13
|
||||
1,-13
|
||||
2,-13
|
||||
3,-13
|
||||
4,-13
|
||||
5,-13
|
||||
6,-13
|
||||
7,-13
|
||||
8,-13
|
||||
9,-13
|
||||
10,-13
|
||||
11,-13
|
||||
12,-13
|
||||
13,-13
|
||||
14,-13
|
||||
15,-13
|
||||
16,-13
|
||||
17,-13
|
||||
18,-13
|
||||
19,-13
|
||||
|
@@ -1,401 +0,0 @@
|
||||
episodes,rewards
|
||||
0,-2131
|
||||
1,-1086
|
||||
2,-586
|
||||
3,-220
|
||||
4,-154
|
||||
5,-122
|
||||
6,-150
|
||||
7,-159
|
||||
8,-164
|
||||
9,-88
|
||||
10,-195
|
||||
11,-114
|
||||
12,-60
|
||||
13,-179
|
||||
14,-101
|
||||
15,-304
|
||||
16,-96
|
||||
17,-119
|
||||
18,-113
|
||||
19,-98
|
||||
20,-106
|
||||
21,-105
|
||||
22,-77
|
||||
23,-51
|
||||
24,-105
|
||||
25,-136
|
||||
26,-100
|
||||
27,-29
|
||||
28,-79
|
||||
29,-114
|
||||
30,-82
|
||||
31,-70
|
||||
32,-75
|
||||
33,-51
|
||||
34,-94
|
||||
35,-52
|
||||
36,-93
|
||||
37,-71
|
||||
38,-73
|
||||
39,-48
|
||||
40,-52
|
||||
41,-96
|
||||
42,-46
|
||||
43,-65
|
||||
44,-57
|
||||
45,-41
|
||||
46,-104
|
||||
47,-51
|
||||
48,-181
|
||||
49,-229
|
||||
50,-39
|
||||
51,-69
|
||||
52,-53
|
||||
53,-59
|
||||
54,-26
|
||||
55,-75
|
||||
56,-31
|
||||
57,-60
|
||||
58,-63
|
||||
59,-40
|
||||
60,-35
|
||||
61,-79
|
||||
62,-42
|
||||
63,-22
|
||||
64,-73
|
||||
65,-71
|
||||
66,-18
|
||||
67,-55
|
||||
68,-29
|
||||
69,-43
|
||||
70,-70
|
||||
71,-49
|
||||
72,-42
|
||||
73,-29
|
||||
74,-81
|
||||
75,-36
|
||||
76,-38
|
||||
77,-36
|
||||
78,-52
|
||||
79,-28
|
||||
80,-42
|
||||
81,-52
|
||||
82,-66
|
||||
83,-31
|
||||
84,-27
|
||||
85,-49
|
||||
86,-28
|
||||
87,-54
|
||||
88,-34
|
||||
89,-35
|
||||
90,-50
|
||||
91,-36
|
||||
92,-36
|
||||
93,-46
|
||||
94,-34
|
||||
95,-135
|
||||
96,-39
|
||||
97,-36
|
||||
98,-26
|
||||
99,-56
|
||||
100,-40
|
||||
101,-40
|
||||
102,-26
|
||||
103,-28
|
||||
104,-31
|
||||
105,-35
|
||||
106,-26
|
||||
107,-57
|
||||
108,-44
|
||||
109,-41
|
||||
110,-31
|
||||
111,-26
|
||||
112,-25
|
||||
113,-41
|
||||
114,-32
|
||||
115,-44
|
||||
116,-30
|
||||
117,-32
|
||||
118,-30
|
||||
119,-25
|
||||
120,-23
|
||||
121,-47
|
||||
122,-24
|
||||
123,-45
|
||||
124,-39
|
||||
125,-21
|
||||
126,-43
|
||||
127,-143
|
||||
128,-26
|
||||
129,-20
|
||||
130,-32
|
||||
131,-16
|
||||
132,-24
|
||||
133,-42
|
||||
134,-25
|
||||
135,-36
|
||||
136,-19
|
||||
137,-29
|
||||
138,-43
|
||||
139,-17
|
||||
140,-150
|
||||
141,-32
|
||||
142,-34
|
||||
143,-19
|
||||
144,-26
|
||||
145,-30
|
||||
146,-31
|
||||
147,-49
|
||||
148,-33
|
||||
149,-21
|
||||
150,-17
|
||||
151,-48
|
||||
152,-34
|
||||
153,-20
|
||||
154,-20
|
||||
155,-26
|
||||
156,-21
|
||||
157,-13
|
||||
158,-40
|
||||
159,-22
|
||||
160,-26
|
||||
161,-30
|
||||
162,-29
|
||||
163,-25
|
||||
164,-26
|
||||
165,-27
|
||||
166,-21
|
||||
167,-29
|
||||
168,-24
|
||||
169,-17
|
||||
170,-22
|
||||
171,-35
|
||||
172,-35
|
||||
173,-18
|
||||
174,-135
|
||||
175,-15
|
||||
176,-23
|
||||
177,-28
|
||||
178,-25
|
||||
179,-24
|
||||
180,-29
|
||||
181,-31
|
||||
182,-24
|
||||
183,-129
|
||||
184,-45
|
||||
185,-24
|
||||
186,-17
|
||||
187,-20
|
||||
188,-21
|
||||
189,-23
|
||||
190,-15
|
||||
191,-32
|
||||
192,-22
|
||||
193,-19
|
||||
194,-17
|
||||
195,-45
|
||||
196,-15
|
||||
197,-14
|
||||
198,-14
|
||||
199,-37
|
||||
200,-23
|
||||
201,-17
|
||||
202,-19
|
||||
203,-21
|
||||
204,-23
|
||||
205,-27
|
||||
206,-14
|
||||
207,-18
|
||||
208,-23
|
||||
209,-34
|
||||
210,-23
|
||||
211,-13
|
||||
212,-25
|
||||
213,-17
|
||||
214,-13
|
||||
215,-21
|
||||
216,-29
|
||||
217,-18
|
||||
218,-24
|
||||
219,-15
|
||||
220,-27
|
||||
221,-25
|
||||
222,-21
|
||||
223,-19
|
||||
224,-17
|
||||
225,-18
|
||||
226,-13
|
||||
227,-22
|
||||
228,-14
|
||||
229,-13
|
||||
230,-29
|
||||
231,-23
|
||||
232,-15
|
||||
233,-15
|
||||
234,-14
|
||||
235,-28
|
||||
236,-25
|
||||
237,-17
|
||||
238,-23
|
||||
239,-29
|
||||
240,-15
|
||||
241,-14
|
||||
242,-15
|
||||
243,-23
|
||||
244,-15
|
||||
245,-16
|
||||
246,-19
|
||||
247,-13
|
||||
248,-16
|
||||
249,-17
|
||||
250,-25
|
||||
251,-30
|
||||
252,-13
|
||||
253,-14
|
||||
254,-15
|
||||
255,-22
|
||||
256,-14
|
||||
257,-17
|
||||
258,-126
|
||||
259,-15
|
||||
260,-21
|
||||
261,-16
|
||||
262,-23
|
||||
263,-14
|
||||
264,-13
|
||||
265,-13
|
||||
266,-19
|
||||
267,-13
|
||||
268,-19
|
||||
269,-17
|
||||
270,-17
|
||||
271,-13
|
||||
272,-19
|
||||
273,-13
|
||||
274,-13
|
||||
275,-16
|
||||
276,-22
|
||||
277,-14
|
||||
278,-15
|
||||
279,-19
|
||||
280,-34
|
||||
281,-13
|
||||
282,-15
|
||||
283,-32
|
||||
284,-13
|
||||
285,-13
|
||||
286,-13
|
||||
287,-14
|
||||
288,-16
|
||||
289,-13
|
||||
290,-13
|
||||
291,-17
|
||||
292,-13
|
||||
293,-13
|
||||
294,-22
|
||||
295,-14
|
||||
296,-15
|
||||
297,-13
|
||||
298,-13
|
||||
299,-13
|
||||
300,-16
|
||||
301,-13
|
||||
302,-14
|
||||
303,-13
|
||||
304,-13
|
||||
305,-13
|
||||
306,-24
|
||||
307,-13
|
||||
308,-13
|
||||
309,-15
|
||||
310,-13
|
||||
311,-13
|
||||
312,-13
|
||||
313,-15
|
||||
314,-13
|
||||
315,-19
|
||||
316,-15
|
||||
317,-17
|
||||
318,-13
|
||||
319,-13
|
||||
320,-13
|
||||
321,-13
|
||||
322,-13
|
||||
323,-15
|
||||
324,-13
|
||||
325,-13
|
||||
326,-13
|
||||
327,-123
|
||||
328,-13
|
||||
329,-13
|
||||
330,-13
|
||||
331,-13
|
||||
332,-13
|
||||
333,-13
|
||||
334,-13
|
||||
335,-13
|
||||
336,-16
|
||||
337,-13
|
||||
338,-23
|
||||
339,-13
|
||||
340,-13
|
||||
341,-13
|
||||
342,-13
|
||||
343,-13
|
||||
344,-13
|
||||
345,-13
|
||||
346,-13
|
||||
347,-13
|
||||
348,-13
|
||||
349,-13
|
||||
350,-134
|
||||
351,-13
|
||||
352,-13
|
||||
353,-13
|
||||
354,-13
|
||||
355,-13
|
||||
356,-13
|
||||
357,-13
|
||||
358,-13
|
||||
359,-13
|
||||
360,-15
|
||||
361,-13
|
||||
362,-13
|
||||
363,-13
|
||||
364,-13
|
||||
365,-13
|
||||
366,-13
|
||||
367,-13
|
||||
368,-13
|
||||
369,-14
|
||||
370,-13
|
||||
371,-13
|
||||
372,-13
|
||||
373,-13
|
||||
374,-13
|
||||
375,-13
|
||||
376,-13
|
||||
377,-124
|
||||
378,-13
|
||||
379,-13
|
||||
380,-13
|
||||
381,-13
|
||||
382,-13
|
||||
383,-13
|
||||
384,-13
|
||||
385,-13
|
||||
386,-13
|
||||
387,-13
|
||||
388,-13
|
||||
389,-121
|
||||
390,-13
|
||||
391,-13
|
||||
392,-13
|
||||
393,-13
|
||||
394,-13
|
||||
395,-13
|
||||
396,-13
|
||||
397,-13
|
||||
398,-17
|
||||
399,-13
|
||||
|
Binary file not shown.
@@ -0,0 +1 @@
|
||||
{"algo_name": "Q-learning", "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": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\QLearning/outputs/CliffWalking-v0/20220826-224730/results/", "model_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\QLearning/outputs/CliffWalking-v0/20220826-224730/models/", "n_states": 48, "n_actions": 4}
|
||||
|
Before Width: | Height: | Size: 24 KiB After Width: | Height: | Size: 24 KiB |
@@ -0,0 +1,21 @@
|
||||
episodes,rewards,steps
|
||||
0,-13,13
|
||||
1,-13,13
|
||||
2,-13,13
|
||||
3,-13,13
|
||||
4,-13,13
|
||||
5,-13,13
|
||||
6,-13,13
|
||||
7,-13,13
|
||||
8,-13,13
|
||||
9,-13,13
|
||||
10,-13,13
|
||||
11,-13,13
|
||||
12,-13,13
|
||||
13,-13,13
|
||||
14,-13,13
|
||||
15,-13,13
|
||||
16,-13,13
|
||||
17,-13,13
|
||||
18,-13,13
|
||||
19,-13,13
|
||||
|
|
Before Width: | Height: | Size: 35 KiB After Width: | Height: | Size: 35 KiB |
@@ -0,0 +1,401 @@
|
||||
episodes,rewards,steps
|
||||
0,-2131,448
|
||||
1,-1086,492
|
||||
2,-586,388
|
||||
3,-220,220
|
||||
4,-154,154
|
||||
5,-122,122
|
||||
6,-150,150
|
||||
7,-159,159
|
||||
8,-164,164
|
||||
9,-88,88
|
||||
10,-195,195
|
||||
11,-114,114
|
||||
12,-60,60
|
||||
13,-179,179
|
||||
14,-101,101
|
||||
15,-304,205
|
||||
16,-96,96
|
||||
17,-119,119
|
||||
18,-113,113
|
||||
19,-98,98
|
||||
20,-106,106
|
||||
21,-105,105
|
||||
22,-77,77
|
||||
23,-51,51
|
||||
24,-105,105
|
||||
25,-136,136
|
||||
26,-100,100
|
||||
27,-29,29
|
||||
28,-79,79
|
||||
29,-114,114
|
||||
30,-82,82
|
||||
31,-70,70
|
||||
32,-75,75
|
||||
33,-51,51
|
||||
34,-94,94
|
||||
35,-52,52
|
||||
36,-93,93
|
||||
37,-71,71
|
||||
38,-73,73
|
||||
39,-48,48
|
||||
40,-52,52
|
||||
41,-96,96
|
||||
42,-46,46
|
||||
43,-65,65
|
||||
44,-57,57
|
||||
45,-41,41
|
||||
46,-104,104
|
||||
47,-51,51
|
||||
48,-181,82
|
||||
49,-229,130
|
||||
50,-39,39
|
||||
51,-69,69
|
||||
52,-53,53
|
||||
53,-59,59
|
||||
54,-26,26
|
||||
55,-75,75
|
||||
56,-31,31
|
||||
57,-60,60
|
||||
58,-63,63
|
||||
59,-40,40
|
||||
60,-35,35
|
||||
61,-79,79
|
||||
62,-42,42
|
||||
63,-22,22
|
||||
64,-73,73
|
||||
65,-71,71
|
||||
66,-18,18
|
||||
67,-55,55
|
||||
68,-29,29
|
||||
69,-43,43
|
||||
70,-70,70
|
||||
71,-49,49
|
||||
72,-42,42
|
||||
73,-29,29
|
||||
74,-81,81
|
||||
75,-36,36
|
||||
76,-38,38
|
||||
77,-36,36
|
||||
78,-52,52
|
||||
79,-28,28
|
||||
80,-42,42
|
||||
81,-52,52
|
||||
82,-66,66
|
||||
83,-31,31
|
||||
84,-27,27
|
||||
85,-49,49
|
||||
86,-28,28
|
||||
87,-54,54
|
||||
88,-34,34
|
||||
89,-35,35
|
||||
90,-50,50
|
||||
91,-36,36
|
||||
92,-36,36
|
||||
93,-46,46
|
||||
94,-34,34
|
||||
95,-135,36
|
||||
96,-39,39
|
||||
97,-36,36
|
||||
98,-26,26
|
||||
99,-56,56
|
||||
100,-40,40
|
||||
101,-40,40
|
||||
102,-26,26
|
||||
103,-28,28
|
||||
104,-31,31
|
||||
105,-35,35
|
||||
106,-26,26
|
||||
107,-57,57
|
||||
108,-44,44
|
||||
109,-41,41
|
||||
110,-31,31
|
||||
111,-26,26
|
||||
112,-25,25
|
||||
113,-41,41
|
||||
114,-32,32
|
||||
115,-44,44
|
||||
116,-30,30
|
||||
117,-32,32
|
||||
118,-30,30
|
||||
119,-25,25
|
||||
120,-23,23
|
||||
121,-47,47
|
||||
122,-24,24
|
||||
123,-45,45
|
||||
124,-39,39
|
||||
125,-21,21
|
||||
126,-43,43
|
||||
127,-143,44
|
||||
128,-26,26
|
||||
129,-20,20
|
||||
130,-32,32
|
||||
131,-16,16
|
||||
132,-24,24
|
||||
133,-42,42
|
||||
134,-25,25
|
||||
135,-36,36
|
||||
136,-19,19
|
||||
137,-29,29
|
||||
138,-43,43
|
||||
139,-17,17
|
||||
140,-150,51
|
||||
141,-32,32
|
||||
142,-34,34
|
||||
143,-19,19
|
||||
144,-26,26
|
||||
145,-30,30
|
||||
146,-31,31
|
||||
147,-49,49
|
||||
148,-33,33
|
||||
149,-21,21
|
||||
150,-17,17
|
||||
151,-48,48
|
||||
152,-34,34
|
||||
153,-20,20
|
||||
154,-20,20
|
||||
155,-26,26
|
||||
156,-21,21
|
||||
157,-13,13
|
||||
158,-40,40
|
||||
159,-22,22
|
||||
160,-26,26
|
||||
161,-30,30
|
||||
162,-29,29
|
||||
163,-25,25
|
||||
164,-26,26
|
||||
165,-27,27
|
||||
166,-21,21
|
||||
167,-29,29
|
||||
168,-24,24
|
||||
169,-17,17
|
||||
170,-22,22
|
||||
171,-35,35
|
||||
172,-35,35
|
||||
173,-18,18
|
||||
174,-135,36
|
||||
175,-15,15
|
||||
176,-23,23
|
||||
177,-28,28
|
||||
178,-25,25
|
||||
179,-24,24
|
||||
180,-29,29
|
||||
181,-31,31
|
||||
182,-24,24
|
||||
183,-129,30
|
||||
184,-45,45
|
||||
185,-24,24
|
||||
186,-17,17
|
||||
187,-20,20
|
||||
188,-21,21
|
||||
189,-23,23
|
||||
190,-15,15
|
||||
191,-32,32
|
||||
192,-22,22
|
||||
193,-19,19
|
||||
194,-17,17
|
||||
195,-45,45
|
||||
196,-15,15
|
||||
197,-14,14
|
||||
198,-14,14
|
||||
199,-37,37
|
||||
200,-23,23
|
||||
201,-17,17
|
||||
202,-19,19
|
||||
203,-21,21
|
||||
204,-23,23
|
||||
205,-27,27
|
||||
206,-14,14
|
||||
207,-18,18
|
||||
208,-23,23
|
||||
209,-34,34
|
||||
210,-23,23
|
||||
211,-13,13
|
||||
212,-25,25
|
||||
213,-17,17
|
||||
214,-13,13
|
||||
215,-21,21
|
||||
216,-29,29
|
||||
217,-18,18
|
||||
218,-24,24
|
||||
219,-15,15
|
||||
220,-27,27
|
||||
221,-25,25
|
||||
222,-21,21
|
||||
223,-19,19
|
||||
224,-17,17
|
||||
225,-18,18
|
||||
226,-13,13
|
||||
227,-22,22
|
||||
228,-14,14
|
||||
229,-13,13
|
||||
230,-29,29
|
||||
231,-23,23
|
||||
232,-15,15
|
||||
233,-15,15
|
||||
234,-14,14
|
||||
235,-28,28
|
||||
236,-25,25
|
||||
237,-17,17
|
||||
238,-23,23
|
||||
239,-29,29
|
||||
240,-15,15
|
||||
241,-14,14
|
||||
242,-15,15
|
||||
243,-23,23
|
||||
244,-15,15
|
||||
245,-16,16
|
||||
246,-19,19
|
||||
247,-13,13
|
||||
248,-16,16
|
||||
249,-17,17
|
||||
250,-25,25
|
||||
251,-30,30
|
||||
252,-13,13
|
||||
253,-14,14
|
||||
254,-15,15
|
||||
255,-22,22
|
||||
256,-14,14
|
||||
257,-17,17
|
||||
258,-126,27
|
||||
259,-15,15
|
||||
260,-21,21
|
||||
261,-16,16
|
||||
262,-23,23
|
||||
263,-14,14
|
||||
264,-13,13
|
||||
265,-13,13
|
||||
266,-19,19
|
||||
267,-13,13
|
||||
268,-19,19
|
||||
269,-17,17
|
||||
270,-17,17
|
||||
271,-13,13
|
||||
272,-19,19
|
||||
273,-13,13
|
||||
274,-13,13
|
||||
275,-16,16
|
||||
276,-22,22
|
||||
277,-14,14
|
||||
278,-15,15
|
||||
279,-19,19
|
||||
280,-34,34
|
||||
281,-13,13
|
||||
282,-15,15
|
||||
283,-32,32
|
||||
284,-13,13
|
||||
285,-13,13
|
||||
286,-13,13
|
||||
287,-14,14
|
||||
288,-16,16
|
||||
289,-13,13
|
||||
290,-13,13
|
||||
291,-17,17
|
||||
292,-13,13
|
||||
293,-13,13
|
||||
294,-22,22
|
||||
295,-14,14
|
||||
296,-15,15
|
||||
297,-13,13
|
||||
298,-13,13
|
||||
299,-13,13
|
||||
300,-16,16
|
||||
301,-13,13
|
||||
302,-14,14
|
||||
303,-13,13
|
||||
304,-13,13
|
||||
305,-13,13
|
||||
306,-24,24
|
||||
307,-13,13
|
||||
308,-13,13
|
||||
309,-15,15
|
||||
310,-13,13
|
||||
311,-13,13
|
||||
312,-13,13
|
||||
313,-15,15
|
||||
314,-13,13
|
||||
315,-19,19
|
||||
316,-15,15
|
||||
317,-17,17
|
||||
318,-13,13
|
||||
319,-13,13
|
||||
320,-13,13
|
||||
321,-13,13
|
||||
322,-13,13
|
||||
323,-15,15
|
||||
324,-13,13
|
||||
325,-13,13
|
||||
326,-13,13
|
||||
327,-123,24
|
||||
328,-13,13
|
||||
329,-13,13
|
||||
330,-13,13
|
||||
331,-13,13
|
||||
332,-13,13
|
||||
333,-13,13
|
||||
334,-13,13
|
||||
335,-13,13
|
||||
336,-16,16
|
||||
337,-13,13
|
||||
338,-23,23
|
||||
339,-13,13
|
||||
340,-13,13
|
||||
341,-13,13
|
||||
342,-13,13
|
||||
343,-13,13
|
||||
344,-13,13
|
||||
345,-13,13
|
||||
346,-13,13
|
||||
347,-13,13
|
||||
348,-13,13
|
||||
349,-13,13
|
||||
350,-134,35
|
||||
351,-13,13
|
||||
352,-13,13
|
||||
353,-13,13
|
||||
354,-13,13
|
||||
355,-13,13
|
||||
356,-13,13
|
||||
357,-13,13
|
||||
358,-13,13
|
||||
359,-13,13
|
||||
360,-15,15
|
||||
361,-13,13
|
||||
362,-13,13
|
||||
363,-13,13
|
||||
364,-13,13
|
||||
365,-13,13
|
||||
366,-13,13
|
||||
367,-13,13
|
||||
368,-13,13
|
||||
369,-14,14
|
||||
370,-13,13
|
||||
371,-13,13
|
||||
372,-13,13
|
||||
373,-13,13
|
||||
374,-13,13
|
||||
375,-13,13
|
||||
376,-13,13
|
||||
377,-124,25
|
||||
378,-13,13
|
||||
379,-13,13
|
||||
380,-13,13
|
||||
381,-13,13
|
||||
382,-13,13
|
||||
383,-13,13
|
||||
384,-13,13
|
||||
385,-13,13
|
||||
386,-13,13
|
||||
387,-13,13
|
||||
388,-13,13
|
||||
389,-121,22
|
||||
390,-13,13
|
||||
391,-13,13
|
||||
392,-13,13
|
||||
393,-13,13
|
||||
394,-13,13
|
||||
395,-13,13
|
||||
396,-13,13
|
||||
397,-13,13
|
||||
398,-17,17
|
||||
399,-13,13
|
||||
|
Binary file not shown.
@@ -0,0 +1 @@
|
||||
{"algo_name": "Q-learning", "env_name": "Racetrack-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": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\QLearning/outputs/Racetrack-v0/20220826-224626/results/", "model_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\QLearning/outputs/Racetrack-v0/20220826-224626/models/", "n_states": 4, "n_actions": 9}
|
||||
Binary file not shown.
|
After Width: | Height: | Size: 39 KiB |
@@ -0,0 +1,21 @@
|
||||
episodes,rewards,steps
|
||||
0,-1000,1000
|
||||
1,2,8
|
||||
2,4,6
|
||||
3,3,7
|
||||
4,2,8
|
||||
5,3,7
|
||||
6,4,6
|
||||
7,-1000,1000
|
||||
8,3,7
|
||||
9,-11,11
|
||||
10,-19,19
|
||||
11,-18,18
|
||||
12,1,9
|
||||
13,1,9
|
||||
14,4,6
|
||||
15,-16,16
|
||||
16,-17,17
|
||||
17,4,6
|
||||
18,-16,16
|
||||
19,4,6
|
||||
|
Binary file not shown.
|
After Width: | Height: | Size: 40 KiB |
@@ -0,0 +1,401 @@
|
||||
episodes,rewards,steps
|
||||
0,-3580,1000
|
||||
1,-2960,1000
|
||||
2,-2670,1000
|
||||
3,-2720,1000
|
||||
4,-2670,1000
|
||||
5,-2570,1000
|
||||
6,-2407,977
|
||||
7,-2012,852
|
||||
8,-2500,1000
|
||||
9,-2530,1000
|
||||
10,-2550,1000
|
||||
11,-437,187
|
||||
12,-80,40
|
||||
13,-2450,1000
|
||||
14,-338,148
|
||||
15,-1175,525
|
||||
16,-755,325
|
||||
17,-411,181
|
||||
18,-1068,448
|
||||
19,-785,325
|
||||
20,-149,79
|
||||
21,-628,268
|
||||
22,-423,183
|
||||
23,-282,122
|
||||
24,-2198,938
|
||||
25,-13,13
|
||||
26,-253,113
|
||||
27,-48,28
|
||||
28,-72,42
|
||||
29,-123,63
|
||||
30,-305,145
|
||||
31,-72,32
|
||||
32,-142,72
|
||||
33,-13,13
|
||||
34,4,6
|
||||
35,-1285,545
|
||||
36,-174,94
|
||||
37,-436,196
|
||||
38,-759,339
|
||||
39,-11,11
|
||||
40,-17,17
|
||||
41,-283,123
|
||||
42,-181,81
|
||||
43,-44,24
|
||||
44,-55,35
|
||||
45,-135,65
|
||||
46,-577,277
|
||||
47,-234,114
|
||||
48,-54,34
|
||||
49,4,6
|
||||
50,-29,19
|
||||
51,-100,50
|
||||
52,-32,22
|
||||
53,-23,23
|
||||
54,4,6
|
||||
55,-17,17
|
||||
56,-18,18
|
||||
57,-48,28
|
||||
58,-34,24
|
||||
59,-45,25
|
||||
60,-29,19
|
||||
61,1,9
|
||||
62,-77,37
|
||||
63,3,7
|
||||
64,-25,15
|
||||
65,-3,13
|
||||
66,-78,48
|
||||
67,-69,39
|
||||
68,-105,45
|
||||
69,-48,28
|
||||
70,3,7
|
||||
71,4,6
|
||||
72,-100,50
|
||||
73,-130,60
|
||||
74,-20,20
|
||||
75,4,6
|
||||
76,4,6
|
||||
77,4,6
|
||||
78,4,6
|
||||
79,-47,27
|
||||
80,4,6
|
||||
81,4,6
|
||||
82,-174,94
|
||||
83,-12,12
|
||||
84,-26,16
|
||||
85,3,7
|
||||
86,3,7
|
||||
87,-42,32
|
||||
88,-48,28
|
||||
89,-97,57
|
||||
90,-11,11
|
||||
91,-16,16
|
||||
92,-15,15
|
||||
93,4,6
|
||||
94,-147,67
|
||||
95,-52,32
|
||||
96,-97,47
|
||||
97,3,7
|
||||
98,-17,17
|
||||
99,3,7
|
||||
100,4,6
|
||||
101,3,7
|
||||
102,3,7
|
||||
103,3,7
|
||||
104,1,9
|
||||
105,4,6
|
||||
106,4,6
|
||||
107,3,7
|
||||
108,4,6
|
||||
109,-68,38
|
||||
110,3,7
|
||||
111,4,6
|
||||
112,-14,14
|
||||
113,4,6
|
||||
114,-57,37
|
||||
115,3,7
|
||||
116,4,6
|
||||
117,-12,12
|
||||
118,3,7
|
||||
119,3,7
|
||||
120,-64,34
|
||||
121,-13,13
|
||||
122,3,7
|
||||
123,-13,13
|
||||
124,4,6
|
||||
125,3,7
|
||||
126,-32,22
|
||||
127,-41,31
|
||||
128,3,7
|
||||
129,3,7
|
||||
130,3,7
|
||||
131,4,6
|
||||
132,4,6
|
||||
133,3,7
|
||||
134,-12,12
|
||||
135,-31,21
|
||||
136,4,6
|
||||
137,3,7
|
||||
138,-51,31
|
||||
139,-48,28
|
||||
140,4,6
|
||||
141,-85,45
|
||||
142,-14,14
|
||||
143,4,6
|
||||
144,3,7
|
||||
145,-6,16
|
||||
146,4,6
|
||||
147,4,6
|
||||
148,-15,15
|
||||
149,4,6
|
||||
150,-24,24
|
||||
151,3,7
|
||||
152,-14,14
|
||||
153,-18,18
|
||||
154,3,7
|
||||
155,4,6
|
||||
156,-85,45
|
||||
157,-51,31
|
||||
158,3,7
|
||||
159,2,8
|
||||
160,3,7
|
||||
161,-79,39
|
||||
162,-14,14
|
||||
163,-13,13
|
||||
164,4,6
|
||||
165,3,7
|
||||
166,4,6
|
||||
167,3,7
|
||||
168,-74,34
|
||||
169,-15,15
|
||||
170,4,6
|
||||
171,-14,14
|
||||
172,4,6
|
||||
173,-31,21
|
||||
174,-8,18
|
||||
175,4,6
|
||||
176,4,6
|
||||
177,4,6
|
||||
178,4,6
|
||||
179,-29,19
|
||||
180,4,6
|
||||
181,3,7
|
||||
182,4,6
|
||||
183,-82,42
|
||||
184,3,7
|
||||
185,4,6
|
||||
186,4,6
|
||||
187,-11,11
|
||||
188,-23,23
|
||||
189,-33,23
|
||||
190,3,7
|
||||
191,-12,12
|
||||
192,-44,24
|
||||
193,-62,42
|
||||
194,-16,16
|
||||
195,4,6
|
||||
196,-12,12
|
||||
197,3,7
|
||||
198,-13,13
|
||||
199,3,7
|
||||
200,3,7
|
||||
201,4,6
|
||||
202,4,6
|
||||
203,4,6
|
||||
204,-28,18
|
||||
205,-16,16
|
||||
206,3,7
|
||||
207,4,6
|
||||
208,-12,12
|
||||
209,-13,13
|
||||
210,-66,36
|
||||
211,-14,14
|
||||
212,4,6
|
||||
213,4,6
|
||||
214,-15,15
|
||||
215,-60,30
|
||||
216,4,6
|
||||
217,3,7
|
||||
218,4,6
|
||||
219,-33,23
|
||||
220,-12,12
|
||||
221,-14,14
|
||||
222,4,6
|
||||
223,3,7
|
||||
224,-97,47
|
||||
225,4,6
|
||||
226,2,8
|
||||
227,4,6
|
||||
228,4,6
|
||||
229,3,7
|
||||
230,-11,11
|
||||
231,4,6
|
||||
232,3,7
|
||||
233,3,7
|
||||
234,4,6
|
||||
235,3,7
|
||||
236,3,7
|
||||
237,-32,22
|
||||
238,-13,13
|
||||
239,3,7
|
||||
240,-22,22
|
||||
241,4,6
|
||||
242,2,8
|
||||
243,-31,21
|
||||
244,4,6
|
||||
245,-4,14
|
||||
246,-30,20
|
||||
247,4,6
|
||||
248,3,7
|
||||
249,-26,16
|
||||
250,4,6
|
||||
251,-12,12
|
||||
252,2,8
|
||||
253,1,9
|
||||
254,4,6
|
||||
255,2,8
|
||||
256,2,8
|
||||
257,-12,12
|
||||
258,3,7
|
||||
259,-48,28
|
||||
260,4,6
|
||||
261,4,6
|
||||
262,-51,31
|
||||
263,-12,12
|
||||
264,4,6
|
||||
265,2,8
|
||||
266,2,8
|
||||
267,2,8
|
||||
268,3,7
|
||||
269,4,6
|
||||
270,4,6
|
||||
271,-17,17
|
||||
272,4,6
|
||||
273,-13,13
|
||||
274,-16,16
|
||||
275,-97,57
|
||||
276,3,7
|
||||
277,-1,11
|
||||
278,-32,22
|
||||
279,3,7
|
||||
280,4,6
|
||||
281,3,7
|
||||
282,3,7
|
||||
283,3,7
|
||||
284,3,7
|
||||
285,2,8
|
||||
286,3,7
|
||||
287,-15,15
|
||||
288,2,8
|
||||
289,-18,18
|
||||
290,4,6
|
||||
291,-36,26
|
||||
292,4,6
|
||||
293,4,6
|
||||
294,4,6
|
||||
295,4,6
|
||||
296,-77,47
|
||||
297,-14,14
|
||||
298,3,7
|
||||
299,3,7
|
||||
300,3,7
|
||||
301,4,6
|
||||
302,3,7
|
||||
303,4,6
|
||||
304,-12,12
|
||||
305,-45,35
|
||||
306,-63,43
|
||||
307,2,8
|
||||
308,4,6
|
||||
309,4,6
|
||||
310,-13,13
|
||||
311,4,6
|
||||
312,-13,13
|
||||
313,4,6
|
||||
314,3,7
|
||||
315,-30,20
|
||||
316,-13,13
|
||||
317,3,7
|
||||
318,4,6
|
||||
319,4,6
|
||||
320,-12,12
|
||||
321,-13,13
|
||||
322,3,7
|
||||
323,3,7
|
||||
324,3,7
|
||||
325,3,7
|
||||
326,-36,26
|
||||
327,4,6
|
||||
328,3,7
|
||||
329,3,7
|
||||
330,3,7
|
||||
331,3,7
|
||||
332,-14,14
|
||||
333,-16,16
|
||||
334,3,7
|
||||
335,3,7
|
||||
336,-14,14
|
||||
337,1,9
|
||||
338,2,8
|
||||
339,3,7
|
||||
340,4,6
|
||||
341,-36,26
|
||||
342,-14,14
|
||||
343,-78,48
|
||||
344,2,8
|
||||
345,-37,27
|
||||
346,3,7
|
||||
347,3,7
|
||||
348,-37,27
|
||||
349,-16,16
|
||||
350,4,6
|
||||
351,-15,15
|
||||
352,4,6
|
||||
353,2,8
|
||||
354,-44,24
|
||||
355,-13,13
|
||||
356,-14,14
|
||||
357,-17,17
|
||||
358,-13,13
|
||||
359,3,7
|
||||
360,2,8
|
||||
361,4,6
|
||||
362,3,7
|
||||
363,-5,15
|
||||
364,-14,14
|
||||
365,2,8
|
||||
366,-12,12
|
||||
367,3,7
|
||||
368,4,6
|
||||
369,2,8
|
||||
370,2,8
|
||||
371,1,9
|
||||
372,-16,16
|
||||
373,1,9
|
||||
374,4,6
|
||||
375,-16,16
|
||||
376,3,7
|
||||
377,2,8
|
||||
378,-13,13
|
||||
379,-44,34
|
||||
380,-16,16
|
||||
381,-30,20
|
||||
382,4,6
|
||||
383,4,6
|
||||
384,2,8
|
||||
385,-15,15
|
||||
386,4,6
|
||||
387,3,7
|
||||
388,2,8
|
||||
389,4,6
|
||||
390,2,8
|
||||
391,3,7
|
||||
392,3,7
|
||||
393,-14,14
|
||||
394,-15,15
|
||||
395,3,7
|
||||
396,-13,13
|
||||
397,3,7
|
||||
398,4,6
|
||||
399,3,7
|
||||
|
Reference in New Issue
Block a user