hot update A2C

2022-08-29 15:12:33 +08:00
parent 99a3c1afec
commit 0b0f7e857d
109 changed files with 8213 additions and 1658 deletions
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/params.json
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/params.json
@@ -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
-}
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/testing_results.csv
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/testing_results.csv
@@ -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
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/training_results.csv
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220824-103255/results/training_results.csv
@@ -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
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/models/Qleaning_model.pkl
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/models/Qleaning_model.pkl
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/params.json
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/params.json
@@ -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}
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/testing_curve.png
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/testing_curve.png
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/testing_results.csv
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/testing_results.csv
@@ -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
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/training_curve.png
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/training_curve.png
--- a/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/training_results.csv
+++ b/projects/codes/QLearning/outputs/CliffWalking-v0/20220826-224730/results/training_results.csv
@@ -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
				`@@ -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}