Predict_CartPole-v1_SoftQ
Browse files- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/config.yaml +49 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/logs/log.txt +90 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/1000 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/1500 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/2000 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/2500 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/500 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/best +0 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/tb_logs/interact/events.out.tfevents.1688778274.LAPTOP-L4C8EI5B.44368.0 +3 -0
- ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/tb_logs/policy/events.out.tfevents.1688778274.LAPTOP-L4C8EI5B.44368.1 +3 -0
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/config.yaml
ADDED
@@ -0,0 +1,49 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
general_cfg:
|
2 |
+
algo_name: SoftQ
|
3 |
+
collect_traj: false
|
4 |
+
device: cpu
|
5 |
+
env_name: gym
|
6 |
+
interact_summary_fre: 1
|
7 |
+
load_checkpoint: true
|
8 |
+
load_model_step: best
|
9 |
+
load_path: Train_CartPole-v1_SoftQ_20230705-215318
|
10 |
+
max_episode: 30
|
11 |
+
max_step: 200
|
12 |
+
mode: predict
|
13 |
+
model_save_fre: 500
|
14 |
+
model_summary_fre: 1
|
15 |
+
mp_backend: null
|
16 |
+
n_learners: 1
|
17 |
+
n_workers: 2
|
18 |
+
online_eval: true
|
19 |
+
online_eval_episode: 10
|
20 |
+
seed: 1
|
21 |
+
share_buffer: true
|
22 |
+
algo_cfg:
|
23 |
+
alpha: 4
|
24 |
+
batch_size: 128
|
25 |
+
buffer_size: 100000
|
26 |
+
buffer_type: REPLAY_QUE
|
27 |
+
epsilon_decay: 500
|
28 |
+
epsilon_end: 0.01
|
29 |
+
epsilon_start: 0.95
|
30 |
+
gamma: 0.95
|
31 |
+
lr: 0.0001
|
32 |
+
n_steps_per_learn: 1
|
33 |
+
target_update: 4
|
34 |
+
value_layers:
|
35 |
+
- activation: relu
|
36 |
+
layer_size:
|
37 |
+
- 256
|
38 |
+
layer_type: linear
|
39 |
+
- activation: relu
|
40 |
+
layer_size:
|
41 |
+
- 256
|
42 |
+
layer_type: linear
|
43 |
+
env_cfg:
|
44 |
+
id: CartPole-v1
|
45 |
+
ignore_params:
|
46 |
+
- wrapper
|
47 |
+
- ignore_params
|
48 |
+
render_mode: null
|
49 |
+
wrapper: null
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/logs/log.txt
ADDED
@@ -0,0 +1,90 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - General Configs:
|
2 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
3 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Name Value Type
|
4 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - env_name gym <class 'str'>
|
5 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - algo_name SoftQ <class 'str'>
|
6 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - mode predict <class 'str'>
|
7 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - device cpu <class 'str'>
|
8 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - seed 1 <class 'int'>
|
9 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - max_episode 30 <class 'int'>
|
10 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - max_step 200 <class 'int'>
|
11 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - collect_traj 0 <class 'bool'>
|
12 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - mp_backend None <class 'str'>
|
13 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - n_workers 2 <class 'int'>
|
14 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - n_learners 1 <class 'int'>
|
15 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - share_buffer 1 <class 'bool'>
|
16 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - online_eval 1 <class 'bool'>
|
17 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - online_eval_episode 10 <class 'int'>
|
18 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - model_save_fre 500 <class 'int'>
|
19 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - load_checkpoint 1 <class 'bool'>
|
20 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - load_path Train_CartPole-v1_SoftQ_20230705-215318 <class 'str'>
|
21 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - load_model_step best <class 'str'>
|
22 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - interact_summary_fre 1 <class 'int'>
|
23 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - model_summary_fre 1 <class 'int'>
|
24 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
25 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Algo Configs:
|
26 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
27 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Name Value Type
|
28 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - epsilon_start 0.95 <class 'float'>
|
29 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - epsilon_end 0.01 <class 'float'>
|
30 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - epsilon_decay 500 <class 'int'>
|
31 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - gamma 0.95 <class 'float'>
|
32 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - lr 0.0001 <class 'float'>
|
33 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - buffer_type REPLAY_QUE <class 'str'>
|
34 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - buffer_size 100000 <class 'int'>
|
35 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - batch_size 128 <class 'int'>
|
36 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - alpha 4 <class 'int'>
|
37 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - target_update 4 <class 'int'>
|
38 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - value_layers [{'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}, {'layer_type': 'linear', 'layer_size': [256], 'activation': 'relu'}] <class 'str'>
|
39 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - n_steps_per_learn 1 <class 'int'>
|
40 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
41 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Env Configs:
|
42 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
43 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Name Value Type
|
44 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - id CartPole-v1 <class 'str'>
|
45 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - render_mode None <class 'str'>
|
46 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - wrapper None <class 'str'>
|
47 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ignore_params ['wrapper', 'ignore_params'] <class 'str'>
|
48 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - ================================================================================
|
49 |
+
2023-07-08 09:04:34 - SimpleLog - INFO: - Start predicting!
|
50 |
+
2023-07-08 09:04:35 - SimpleLog - INFO: - Interactor 0 finished episode 1 with reward 200.000 in 200 steps
|
51 |
+
2023-07-08 09:04:35 - SimpleLog - INFO: - Interactor 1 finished episode 2 with reward 200.000 in 200 steps
|
52 |
+
2023-07-08 09:04:36 - SimpleLog - INFO: - Interactor 0 finished episode 3 with reward 200.000 in 200 steps
|
53 |
+
2023-07-08 09:04:36 - SimpleLog - INFO: - Interactor 1 finished episode 4 with reward 200.000 in 200 steps
|
54 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - update_step: 500, online_eval_reward: 200.000
|
55 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
56 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - Interactor 0 finished episode 5 with reward 200.000 in 200 steps
|
57 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - Interactor 1 finished episode 6 with reward 200.000 in 200 steps
|
58 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - Interactor 0 finished episode 7 with reward 200.000 in 200 steps
|
59 |
+
2023-07-08 09:04:37 - SimpleLog - INFO: - Interactor 1 finished episode 8 with reward 200.000 in 200 steps
|
60 |
+
2023-07-08 09:04:38 - SimpleLog - INFO: - Interactor 0 finished episode 9 with reward 200.000 in 200 steps
|
61 |
+
2023-07-08 09:04:38 - SimpleLog - INFO: - Interactor 1 finished episode 10 with reward 200.000 in 200 steps
|
62 |
+
2023-07-08 09:04:39 - SimpleLog - INFO: - update_step: 1000, online_eval_reward: 200.000
|
63 |
+
2023-07-08 09:04:39 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
64 |
+
2023-07-08 09:04:39 - SimpleLog - INFO: - Interactor 0 finished episode 11 with reward 200.000 in 200 steps
|
65 |
+
2023-07-08 09:04:39 - SimpleLog - INFO: - Interactor 1 finished episode 12 with reward 200.000 in 200 steps
|
66 |
+
2023-07-08 09:04:40 - SimpleLog - INFO: - Interactor 0 finished episode 13 with reward 200.000 in 200 steps
|
67 |
+
2023-07-08 09:04:40 - SimpleLog - INFO: - Interactor 1 finished episode 14 with reward 200.000 in 200 steps
|
68 |
+
2023-07-08 09:04:40 - SimpleLog - INFO: - update_step: 1500, online_eval_reward: 200.000
|
69 |
+
2023-07-08 09:04:40 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
70 |
+
2023-07-08 09:04:41 - SimpleLog - INFO: - Interactor 0 finished episode 15 with reward 200.000 in 200 steps
|
71 |
+
2023-07-08 09:04:41 - SimpleLog - INFO: - Interactor 1 finished episode 16 with reward 200.000 in 200 steps
|
72 |
+
2023-07-08 09:04:41 - SimpleLog - INFO: - Interactor 0 finished episode 17 with reward 200.000 in 200 steps
|
73 |
+
2023-07-08 09:04:41 - SimpleLog - INFO: - Interactor 1 finished episode 18 with reward 200.000 in 200 steps
|
74 |
+
2023-07-08 09:04:42 - SimpleLog - INFO: - Interactor 0 finished episode 19 with reward 200.000 in 200 steps
|
75 |
+
2023-07-08 09:04:42 - SimpleLog - INFO: - Interactor 1 finished episode 20 with reward 200.000 in 200 steps
|
76 |
+
2023-07-08 09:04:42 - SimpleLog - INFO: - update_step: 2000, online_eval_reward: 200.000
|
77 |
+
2023-07-08 09:04:42 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
78 |
+
2023-07-08 09:04:43 - SimpleLog - INFO: - Interactor 0 finished episode 21 with reward 200.000 in 200 steps
|
79 |
+
2023-07-08 09:04:43 - SimpleLog - INFO: - Interactor 1 finished episode 22 with reward 200.000 in 200 steps
|
80 |
+
2023-07-08 09:04:44 - SimpleLog - INFO: - Interactor 0 finished episode 23 with reward 200.000 in 200 steps
|
81 |
+
2023-07-08 09:04:44 - SimpleLog - INFO: - Interactor 1 finished episode 24 with reward 200.000 in 200 steps
|
82 |
+
2023-07-08 09:04:44 - SimpleLog - INFO: - update_step: 2500, online_eval_reward: 200.000
|
83 |
+
2023-07-08 09:04:44 - SimpleLog - INFO: - current update step obtain a better online_eval_reward: 200.000, save the best model!
|
84 |
+
2023-07-08 09:04:45 - SimpleLog - INFO: - Interactor 0 finished episode 25 with reward 200.000 in 200 steps
|
85 |
+
2023-07-08 09:04:45 - SimpleLog - INFO: - Interactor 1 finished episode 26 with reward 200.000 in 200 steps
|
86 |
+
2023-07-08 09:04:45 - SimpleLog - INFO: - Interactor 0 finished episode 27 with reward 200.000 in 200 steps
|
87 |
+
2023-07-08 09:04:45 - SimpleLog - INFO: - Interactor 1 finished episode 28 with reward 200.000 in 200 steps
|
88 |
+
2023-07-08 09:04:46 - SimpleLog - INFO: - Interactor 0 finished episode 29 with reward 200.000 in 200 steps
|
89 |
+
2023-07-08 09:04:46 - SimpleLog - INFO: - Interactor 1 finished episode 30 with reward 200.000 in 200 steps
|
90 |
+
2023-07-08 09:04:46 - SimpleLog - INFO: - Finish predicting! Time cost: 11.327 s
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/1000
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:3aff86a89801bf007bd42a26cb8379736ad5f79d5aec13fef527579c67766b14
|
3 |
+
size 544727
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/1500
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:88cf9bd409af41977624c975c2732f8a6cd83c707e04326c5def695931ca5262
|
3 |
+
size 544727
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/2000
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:847e40b2f6666c4a0bf2a3c47c84bd2d97ad14fba7f80abdcb800d17cd9e4bf3
|
3 |
+
size 544727
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/2500
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:05143274a91f1d1aeb0b8ef069ad172f7861474fb74cf7b1e118b7c2e7af8ca4
|
3 |
+
size 544727
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/500
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:268334ec7b2a74fca824642b2266262f95fb97f907074b8d7d7f26ec17cc3637
|
3 |
+
size 544713
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/models/best
ADDED
Binary file (545 kB). View file
|
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/tb_logs/interact/events.out.tfevents.1688778274.LAPTOP-L4C8EI5B.44368.0
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:e84a45da666de552b82238f79db89fc70455e38efdbb6f137ceacb585c8ade4a
|
3 |
+
size 3148
|
ClassControl/CartPole-v1/Predict_CartPole-v1_SoftQ_20230708-090434/tb_logs/policy/events.out.tfevents.1688778274.LAPTOP-L4C8EI5B.44368.1
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:de985e2d617c6cf48abe7657d1671e1b47fe5db32586d13d14a8708a9337227f
|
3 |
+
size 150073
|