更新PPO，增加PER DQN

projects/codes/PER_DQN/Test_CartPole-v1_PER_DQN_20221114-104649/config.yaml

@@ -0,0 +1,25 @@
+general_cfg:
+  algo_name: PER_DQN
+  device: cpu
+  env_name: CartPole-v1
+  eval_eps: 10
+  eval_per_episode: 5
+  load_checkpoint: true
+  load_path: Train_CartPole-v1_PER_DQN_20221113-162804
+  max_steps: 200
+  mode: test
+  save_fig: true
+  seed: 0
+  show_fig: false
+  test_eps: 10
+  train_eps: 200
+algo_cfg:
+  batch_size: 64
+  buffer_size: 100000
+  epsilon_decay: 500
+  epsilon_end: 0.01
+  epsilon_start: 0.95
+  gamma: 0.95
+  hidden_dim: 256
+  lr: 0.0001
+  target_update: 4

projects/codes/PER_DQN/Test_CartPole-v1_PER_DQN_20221114-104649/logs/log.txt

@@ -0,0 +1,14 @@
+2022-11-14 10:46:49 - r - INFO: - n_states: 4, n_actions: 2
+2022-11-14 10:46:49 - r - INFO: - Start testing!
+2022-11-14 10:46:49 - r - INFO: - Env: CartPole-v1, Algorithm: PER_DQN, Device: cpu
+2022-11-14 10:46:49 - r - INFO: - Episode: 1/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 2/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 3/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 4/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 5/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 6/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 7/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 8/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 9/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Episode: 10/10, Reward: 200.000, Step: 200
+2022-11-14 10:46:49 - r - INFO: - Finish testing!

projects/codes/PER_DQN/Test_CartPole-v1_PER_DQN_20221114-104649/results/res.csv

@@ -0,0 +1,11 @@
+episodes,rewards,steps
+0,200.0,200
+1,200.0,200
+2,200.0,200
+3,200.0,200
+4,200.0,200
+5,200.0,200
+6,200.0,200
+7,200.0,200
+8,200.0,200
+9,200.0,200