更新算法模版

projects/codes/PPO/outputs/CartPole-v0/20220731-233512/results/params.json

@@ -1,20 +0,0 @@
-{
-    "algo_name": "PPO",
-    "env_name": "CartPole-v0",
-    "continuous": false,
-    "train_eps": 200,
-    "test_eps": 20,
-    "gamma": 0.99,
-    "batch_size": 5,
-    "n_epochs": 4,
-    "actor_lr": 0.0003,
-    "critic_lr": 0.0003,
-    "gae_lambda": 0.95,
-    "policy_clip": 0.2,
-    "update_fre": 20,
-    "hidden_dim": 256,
-    "device": "cpu",
-    "result_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\PPO/outputs/CartPole-v0/20220731-233512/results/",
-    "model_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\PPO/outputs/CartPole-v0/20220731-233512/models/",
-    "save_fig": true
-}

projects/codes/PPO/outputs/CartPole-v0/20220920-213310/results/params.json

@@ -0,0 +1,25 @@
+{
+    "algo_name": "PPO",
+    "env_name": "CartPole-v0",
+    "continuous": false,
+    "train_eps": 200,
+    "test_eps": 20,
+    "gamma": 0.99,
+    "batch_size": 5,
+    "n_epochs": 4,
+    "actor_lr": 0.0003,
+    "critic_lr": 0.0003,
+    "gae_lambda": 0.95,
+    "policy_clip": 0.2,
+    "update_fre": 20,
+    "actor_hidden_dim": 256,
+    "critic_hidden_dim": 256,
+    "device": "cpu",
+    "seed": 10,
+    "show_fig": false,
+    "save_fig": true,
+    "result_path": "c:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\PPO/outputs/CartPole-v0/20220920-213310/results/",
+    "model_path": "c:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\PPO/outputs/CartPole-v0/20220920-213310/models/",
+    "n_states": 4,
+    "n_actions": 2
+}

projects/codes/PPO/outputs/CartPole-v0/20220920-213310/results/testing_results.csv

@@ -0,0 +1,21 @@
+episodes,rewards
+0,200.0
+1,200.0
+2,200.0
+3,200.0
+4,200.0
+5,200.0
+6,200.0
+7,200.0
+8,200.0
+9,200.0
+10,200.0
+11,200.0
+12,200.0
+13,200.0
+14,200.0
+15,200.0
+16,200.0
+17,200.0
+18,200.0
+19,200.0

projects/codes/PPO/outputs/CartPole-v0/20220920-213310/results/training_results.csv

@@ -0,0 +1,201 @@
+episodes,rewards
+0,34.0
+1,12.0
+2,47.0
+3,29.0
+4,20.0
+5,23.0
+6,33.0
+7,25.0
+8,11.0
+9,30.0
+10,18.0
+11,16.0
+12,15.0
+13,25.0
+14,33.0
+15,19.0
+16,50.0
+17,23.0
+18,21.0
+19,42.0
+20,60.0
+21,64.0
+22,30.0
+23,31.0
+24,90.0
+25,43.0
+26,54.0
+27,74.0
+28,30.0
+29,82.0
+30,50.0
+31,53.0
+32,25.0
+33,27.0
+34,145.0
+35,118.0
+36,141.0
+37,148.0
+38,200.0
+39,191.0
+40,71.0
+41,105.0
+42,100.0
+43,120.0
+44,80.0
+45,40.0
+46,104.0
+47,39.0
+48,89.0
+49,60.0
+50,30.0
+51,24.0
+52,20.0
+53,23.0
+54,30.0
+55,32.0
+56,20.0
+57,12.0
+58,25.0
+59,25.0
+60,24.0
+61,29.0
+62,200.0
+63,62.0
+64,200.0
+65,58.0
+66,81.0
+67,200.0
+68,52.0
+69,140.0
+70,200.0
+71,74.0
+72,200.0
+73,29.0
+74,124.0
+75,129.0
+76,200.0
+77,194.0
+78,175.0
+79,117.0
+80,200.0
+81,186.0
+82,114.0
+83,200.0
+84,166.0
+85,150.0
+86,135.0
+87,200.0
+88,200.0
+89,133.0
+90,111.0
+91,200.0
+92,90.0
+93,200.0
+94,147.0
+95,30.0
+96,137.0
+97,200.0
+98,200.0
+99,179.0
+100,167.0
+101,186.0
+102,169.0
+103,200.0
+104,200.0
+105,171.0
+106,200.0
+107,181.0
+108,125.0
+109,200.0
+110,200.0
+111,122.0
+112,200.0
+113,124.0
+114,95.0
+115,102.0
+116,118.0
+117,91.0
+118,64.0
+119,124.0
+120,122.0
+121,76.0
+122,68.0
+123,40.0
+124,52.0
+125,51.0
+126,50.0
+127,49.0
+128,37.0
+129,76.0
+130,83.0
+131,76.0
+132,92.0
+133,113.0
+134,94.0
+135,157.0
+136,92.0
+137,200.0
+138,123.0
+139,200.0
+140,200.0
+141,200.0
+142,140.0
+143,200.0
+144,200.0
+145,200.0
+146,200.0
+147,200.0
+148,200.0
+149,200.0
+150,200.0
+151,78.0
+152,200.0
+153,200.0
+154,200.0
+155,200.0
+156,200.0
+157,200.0
+158,200.0
+159,200.0
+160,200.0
+161,200.0
+162,107.0
+163,187.0
+164,200.0
+165,200.0
+166,200.0
+167,200.0
+168,200.0
+169,200.0
+170,200.0
+171,200.0
+172,200.0
+173,200.0
+174,200.0
+175,200.0
+176,200.0
+177,200.0
+178,200.0
+179,200.0
+180,200.0
+181,200.0
+182,200.0
+183,200.0
+184,200.0
+185,200.0
+186,200.0
+187,200.0
+188,200.0
+189,200.0
+190,200.0
+191,200.0
+192,200.0
+193,200.0
+194,200.0
+195,200.0
+196,200.0
+197,200.0
+198,200.0
+199,200.0