更新算法模版
This commit is contained in:
@@ -0,0 +1,25 @@
|
||||
general_cfg:
|
||||
algo_name: A2C
|
||||
device: cuda
|
||||
env_name: CartPole-v1
|
||||
eval_eps: 10
|
||||
eval_per_episode: 5
|
||||
load_checkpoint: true
|
||||
load_path: Train_CartPole-v1_A2C_20221031-232138
|
||||
max_steps: 200
|
||||
mode: test
|
||||
save_fig: true
|
||||
seed: 1
|
||||
show_fig: false
|
||||
test_eps: 20
|
||||
train_eps: 1000
|
||||
algo_cfg:
|
||||
actor_hidden_dim: 256
|
||||
actor_lr: 0.0003
|
||||
batch_size: 64
|
||||
buffer_size: 100000
|
||||
critic_hidden_dim: 256
|
||||
critic_lr: 0.001
|
||||
gamma: 0.99
|
||||
hidden_dim: 256
|
||||
target_update: 4
|
||||
@@ -0,0 +1,28 @@
|
||||
2022-10-31 23:33:16 - r - INFO: - n_states: 4, n_actions: 2
|
||||
2022-10-31 23:33:16 - r - INFO: - Actor model name: ActorSoftmaxTanh
|
||||
2022-10-31 23:33:16 - r - INFO: - Critic model name: Critic
|
||||
2022-10-31 23:33:16 - r - INFO: - ACMemory memory name: PGReplay
|
||||
2022-10-31 23:33:16 - r - INFO: - agent name: A2C
|
||||
2022-10-31 23:33:17 - r - INFO: - Start testing!
|
||||
2022-10-31 23:33:17 - r - INFO: - Env: CartPole-v1, Algorithm: A2C, Device: cuda
|
||||
2022-10-31 23:33:18 - r - INFO: - Episode: 1/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:18 - r - INFO: - Episode: 2/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:18 - r - INFO: - Episode: 3/20, Reward: 186.0, Step: 186
|
||||
2022-10-31 23:33:18 - r - INFO: - Episode: 4/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:18 - r - INFO: - Episode: 5/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 6/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 7/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 8/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 9/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 10/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 11/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 12/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 13/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 14/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 15/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 16/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 17/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 18/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:19 - r - INFO: - Episode: 19/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:20 - r - INFO: - Episode: 20/20, Reward: 200.0, Step: 200
|
||||
2022-10-31 23:33:20 - r - INFO: - Finish testing!
|
||||
Binary file not shown.
Binary file not shown.
Binary file not shown.
|
After Width: | Height: | Size: 31 KiB |
@@ -0,0 +1,21 @@
|
||||
episodes,rewards,steps
|
||||
0,200.0,200
|
||||
1,200.0,200
|
||||
2,186.0,186
|
||||
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
|
||||
10,200.0,200
|
||||
11,200.0,200
|
||||
12,200.0,200
|
||||
13,200.0,200
|
||||
14,200.0,200
|
||||
15,200.0,200
|
||||
16,200.0,200
|
||||
17,200.0,200
|
||||
18,200.0,200
|
||||
19,200.0,200
|
||||
|
Reference in New Issue
Block a user