hot update PG

2022-08-25 21:00:53 +08:00
parent 4f4658503e
commit 80f20c73be
34 changed files with 1391 additions and 1695 deletions
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220822-174059/results/params.json
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220822-174059/results/params.json
@@ -1,16 +0,0 @@
-{
-    "algo_name": "PolicyGradient",
-    "env_name": "CartPole-v0",
-    "train_eps": 200,
-    "test_eps": 20,
-    "gamma": 0.99,
-    "lr": 0.005,
-    "update_fre": 8,
-    "hidden_dim": 36,
-    "device": "cpu",
-    "seed": 1,
-    "result_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220822-174059/results/",
-    "model_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220822-174059/models/",
-    "save_fig": true,
-    "show_fig": false
-}
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/models/checkpoint.pt
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/models/checkpoint.pt
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/params.json
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/params.json
@@ -0,0 +1 @@
+{"algo_name": "PolicyGradient", "env_name": "CartPole-v0", "train_eps": 200, "test_eps": 20, "gamma": 0.99, "lr": 0.005, "update_fre": 8, "hidden_dim": 36, "device": "cpu", "seed": 1, "save_fig": true, "show_fig": false, "result_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/models/", "n_states": 4, "n_actions": 2}
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/testing_curve.png
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/testing_curve.png
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/testing_results.csv
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/testing_results.csv
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/training_curve.png
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/training_curve.png
--- a/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/training_results.csv
+++ b/projects/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/training_results.csv
				`@@ -0,0 +1 @@`
				`{"algo_name": "PolicyGradient", "env_name": "CartPole-v0", "train_eps": 200, "test_eps": 20, "gamma": 0.99, "lr": 0.005, "update_fre": 8, "hidden_dim": 36, "device": "cpu", "seed": 1, "save_fig": true, "show_fig": false, "result_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/results/", "model_path": "/Users/jj/Desktop/rl-tutorials/codes/PolicyGradient/outputs/CartPole-v0/20220825-205930/models/", "n_states": 4, "n_actions": 2}`