update

2022-07-21 00:13:44 +08:00
parent bab7f6fe8c
commit 0f38e23baf
34 changed files with 665 additions and 422 deletions
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/models/checkpoint.pth
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/models/checkpoint.pth
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_ma_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_ma_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_rewards_curve.png
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/test_rewards_curve.png
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_ma_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_ma_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_rewards_curve.png
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20211229-145006/results/train_rewards_curve.png
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/models/checkpoint.pth
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/models/checkpoint.pth
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/params.json
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/params.json
@@ -0,0 +1 @@
+{"algo_name": "DoubleDQN", "env_name": "CartPole-v0", "train_eps": 200, "test_eps": 20, "gamma": 0.99, "epsilon_start": 0.95, "epsilon_end": 0.01, "epsilon_decay": 500, "lr": 0.0001, "memory_capacity": 100000, "batch_size": 64, "target_update": 2, "hidden_dim": 256, "device": "cuda", "result_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\DoubleDQN/outputs/CartPole-v0/20220721-000842/results/", "model_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\DoubleDQN/outputs/CartPole-v0/20220721-000842/models/", "save_fig": true}
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_ma_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_ma_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_rewards_curve.png
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/test_rewards_curve.png
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_ma_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_ma_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_rewards.npy
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_rewards.npy
--- a/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_rewards_curve.png
+++ b/codes/DoubleDQN/outputs/CartPole-v0/20220721-000842/results/train_rewards_curve.png
				`@@ -0,0 +1 @@`
				{"algo_name": "DoubleDQN", "env_name": "CartPole-v0", "train_eps": 200, "test_eps": 20, "gamma": 0.99, "epsilon_start": 0.95, "epsilon_end": 0.01, "epsilon_decay": 500, "lr": 0.0001, "memory_capacity": 100000, "batch_size": 64, "target_update": 2, "hidden_dim": 256, "device": "cuda", "result_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\DoubleDQN/outputs/CartPole-v0/20220721-000842/results/", "model_path": "C:\\Users\\24438\\Desktop\\rl-tutorials\\codes\\DoubleDQN/outputs/CartPole-v0/20220721-000842/models/", "save_fig": true}