hot update A2C

projects/codes/Sarsa/outputs/CliffWalking-v0/20220803-142740/results/params.json

@@ -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}

projects/codes/Sarsa/outputs/CliffWalking-v0/20220804-223029/results/params.json

@@ -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
-}

projects/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/results/params.json

@@ -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
+}

projects/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/results/testing_results.csv

@@ -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

projects/codes/Sarsa/outputs/CliffWalking-v0/20220825-213316/results/training_results.csv

@@ -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

projects/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/results/params.json

@@ -0,0 +1 @@
+{"algo_name": "Sarsa", "env_name": "Racetrack-v0", "train_eps": 300, "test_eps": 20, "gamma": 0.99, "epsilon_start": 0.9, "epsilon_end": 0.01, "epsilon_decay": 200, "lr": 0.2, "device": "cpu", "seed": 10, "show_fig": false, "save_fig": true, "result_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/models/", "n_states": 4, "n_actions": 9}

projects/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/results/testing_results.csv

@@ -0,0 +1,21 @@
+episodes,rewards,steps
+0,4,6
+1,4,6
+2,-1010,1000
+3,-14,14
+4,4,6
+5,4,6
+6,4,6
+7,-1060,1000
+8,2,8
+9,-12,12
+10,3,7
+11,-15,15
+12,3,7
+13,4,6
+14,-14,14
+15,3,7
+16,-18,18
+17,4,6
+18,4,6
+19,-1020,1000

projects/codes/Sarsa/outputs/Racetrack-v0/20220825-212738/results/training_results.csv

@@ -0,0 +1,301 @@
+episodes,rewards,steps
+0,-3460,1000
+1,-2800,1000
+2,-2910,1000
+3,-2620,1000
+4,-2620,1000
+5,-2590,1000
+6,-2390,1000
+7,-2510,1000
+8,-2470,1000
+9,-611,251
+10,-891,371
+11,-265,125
+12,-2281,911
+13,-1203,523
+14,-616,266
+15,-213,113
+16,-633,273
+17,-1112,482
+18,-350,160
+19,-852,342
+20,-87,47
+21,-11,11
+22,-27,17
+23,-117,57
+24,-15,15
+25,4,6
+26,-27,17
+27,-94,44
+28,-184,84
+29,-44,24
+30,-150,80
+31,-14,14
+32,-219,89
+33,-50,30
+34,-111,61
+35,-10,10
+36,-28,18
+37,-34,24
+38,-12,12
+39,-19,19
+40,-136,66
+41,-171,71
+42,-51,31
+43,4,6
+44,-117,57
+45,4,6
+46,4,6
+47,-127,67
+48,-78,48
+49,-311,131
+50,-25,15
+51,4,6
+52,-49,29
+53,-25,15
+54,-78,48
+55,-238,108
+56,4,6
+57,-17,17
+58,-29,19
+59,-218,98
+60,4,6
+61,-129,59
+62,-344,144
+63,-25,15
+64,-15,15
+65,-77,37
+66,2,8
+67,0,10
+68,4,6
+69,4,6
+70,-242,102
+71,3,7
+72,4,6
+73,-53,33
+74,-14,14
+75,4,6
+76,4,6
+77,-30,20
+78,-12,12
+79,2,8
+80,-12,12
+81,-150,70
+82,-48,28
+83,-102,52
+84,4,6
+85,-97,47
+86,-10,10
+87,-125,55
+88,-28,18
+89,-26,16
+90,-107,57
+91,4,6
+92,-16,16
+93,-84,44
+94,-13,13
+95,-43,23
+96,-14,14
+97,-12,12
+98,-13,13
+99,-2,12
+100,-14,14
+101,-47,27
+102,4,6
+103,4,6
+104,-91,51
+105,-65,35
+106,4,6
+107,-12,12
+108,-14,14
+109,-13,13
+110,4,6
+111,-41,31
+112,-13,13
+113,4,6
+114,-4,14
+115,-74,34
+116,4,6
+117,-60,30
+118,4,6
+119,-15,15
+120,3,7
+121,4,6
+122,4,6
+123,-19,19
+124,4,6
+125,-49,29
+126,-13,13
+127,-30,20
+128,2,8
+129,-21,21
+130,-45,25
+131,-32,22
+132,-67,37
+133,-46,26
+134,0,10
+135,-12,12
+136,-9,9
+137,-10,10
+138,-14,14
+139,4,6
+140,-11,11
+141,-12,12
+142,2,8
+143,-35,25
+144,4,6
+145,-73,43
+146,4,6
+147,-20,20
+148,4,6
+149,2,8
+150,-29,19
+151,-20,20
+152,4,6
+153,-28,18
+154,4,6
+155,4,6
+156,4,6
+157,4,6
+158,-34,24
+159,4,6
+160,4,6
+161,4,6
+162,-25,15
+163,4,6
+164,3,7
+165,-48,28
+166,4,6
+167,-58,38
+168,-20,20
+169,-9,9
+170,3,7
+171,4,6
+172,3,7
+173,-33,23
+174,-50,30
+175,-16,16
+176,-32,22
+177,-65,35
+178,4,6
+179,-13,13
+180,-11,11
+181,3,7
+182,4,6
+183,-16,16
+184,-12,12
+185,4,6
+186,-48,28
+187,-13,13
+188,2,8
+189,3,7
+190,-27,17
+191,3,7
+192,4,6
+193,4,6
+194,4,6
+195,4,6
+196,4,6
+197,-13,13
+198,-14,14
+199,4,6
+200,4,6
+201,-13,13
+202,-33,23
+203,4,6
+204,-32,22
+205,4,6
+206,-48,28
+207,4,6
+208,4,6
+209,3,7
+210,4,6
+211,-34,24
+212,3,7
+213,4,6
+214,4,6
+215,4,6
+216,3,7
+217,-12,12
+218,3,7
+219,-8,8
+220,3,7
+221,4,6
+222,-46,26
+223,-33,23
+224,4,6
+225,1,9
+226,3,7
+227,2,8
+228,-34,24
+229,4,6
+230,4,6
+231,4,6
+232,4,6
+233,-55,35
+234,-37,27
+235,4,6
+236,-14,14
+237,-65,35
+238,4,6
+239,-13,13
+240,4,6
+241,4,6
+242,-13,13
+243,-30,20
+244,3,7
+245,-13,13
+246,4,6
+247,4,6
+248,-13,13
+249,-32,22
+250,4,6
+251,-55,35
+252,-12,12
+253,3,7
+254,3,7
+255,3,7
+256,4,6
+257,2,8
+258,-12,12
+259,3,7
+260,-10,10
+261,-12,12
+262,4,6
+263,3,7
+264,3,7
+265,-16,16
+266,3,7
+267,-47,27
+268,-13,13
+269,4,6
+270,3,7
+271,-13,13
+272,4,6
+273,4,6
+274,-17,17
+275,4,6
+276,3,7
+277,3,7
+278,4,6
+279,-41,31
+280,3,7
+281,-47,27
+282,-32,22
+283,4,6
+284,3,7
+285,-17,17
+286,3,7
+287,3,7
+288,3,7
+289,-12,12
+290,4,6
+291,3,7
+292,3,7
+293,-24,14
+294,3,7
+295,4,6
+296,3,7
+297,3,7
+298,3,7
+299,-13,13