Hugging Face's logo

jimjiang203
/
rl4greencrab

Model card Files
xet
Community
jimjiang203 commited on
Commit
dbf8752
·
verified ·
1 Parent(s): 37c8108

Upload folder using huggingface_hub

Browse files
Files changed (17) hide show
  1. PPO_gcmenorm.zip +3 -0
  2. RecurrentPPO_gcmenorm_256_1_varR0.3.zip +3 -0
  3. TD3_gcmenorm.zip +3 -0
  4. TQC_gcmenorm.zip +3 -0
  5. data/.ipynb_checkpoints/ppo_env-checkpoint.csv +0 -0
  6. data/ppo_env.csv +0 -0
  7. data/rppo_env.csv +0 -0
  8. data/td3_env.csv +0 -0
  9. data/tqc_env.csv +0 -0
  10. hyperpars/.ipynb_checkpoints/ppo-gcmnorm-checkpoint.yml +17 -0
  11. hyperpars/.ipynb_checkpoints/rppo-gcmnorm-checkpoint.yml +39 -0
  12. hyperpars/.ipynb_checkpoints/td3-gcmnorm-checkpoint.yml +16 -0
  13. hyperpars/.ipynb_checkpoints/tqc-gcmnorm-checkpoint.yml +17 -0
  14. hyperpars/ppo-gcmnorm.yml +17 -0
  15. hyperpars/rppo-gcmnorm.yml +39 -0
  16. hyperpars/td3-gcmnorm.yml +16 -0
  17. hyperpars/tqc-gcmnorm.yml +17 -0
PPO_gcmenorm.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fe270cc55c5453a6df4b5264b9e6df4f615c4195787b73ed22635c5b0a2bec7a
3
+ size 163250
RecurrentPPO_gcmenorm_256_1_varR0.3.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e3f9a33cc90f5c296eff51cdc9128e2dbfccd87788f913c2fd9e2fa09d1b9ab6
3
+ size 9897589
TD3_gcmenorm.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:061f6dc479bb3ff315fbd895bafa2dbcb82d275aace8a88381c1c41aeac51003
3
+ size 6171693
TQC_gcmenorm.zip ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7eaa1c0c21ac455d5493f0f18d6fe439822e033398d7fa3e2938e128ae474396
3
+ size 3362137
data/.ipynb_checkpoints/ppo_env-checkpoint.csv ADDED
The diff for this file is too large to render. See raw diff
 
data/ppo_env.csv ADDED
The diff for this file is too large to render. See raw diff
 
data/rppo_env.csv ADDED
The diff for this file is too large to render. See raw diff
 
data/td3_env.csv ADDED
The diff for this file is too large to render. See raw diff
 
data/tqc_env.csv ADDED
The diff for this file is too large to render. See raw diff
 
hyperpars/.ipynb_checkpoints/ppo-gcmnorm-checkpoint.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "PPO"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0
13
+ use_sde: False
14
+ id: "1"
15
+ repo: "cboettig/rl4geco"
16
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
17
+ progress_bar: True
hyperpars/.ipynb_checkpoints/rppo-gcmnorm-checkpoint.yml ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: 'RecurrentPPO'
2
+ policy: "MultiInputLstmPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 15000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0.3
13
+ model_config:
14
+ 'verbose': 0
15
+ 'normalize_advantage': True
16
+ 'batch_size': 256,
17
+ 'n_steps': 1024,
18
+ 'gamma': 0.9999,
19
+ 'learning_rate': 0.0003,
20
+ 'ent_coef': 0.00429,
21
+ 'clip_range': 0.1,
22
+ 'n_epochs': 10,
23
+ 'gae_lambda': 0.9,
24
+ 'max_grad_norm': 0.5,
25
+ 'vf_coef': 0.19,
26
+ 'use_sde': False
27
+ 'sde_sample_freq': 8
28
+ 'tensorboard_log': "/home/rstudio/logs"
29
+ 'policy_kwargs': dict(log_std_init=0.0,
30
+ ortho_init=False,
31
+ lstm_hidden_size=256,
32
+ n_lstm_layers = 1,
33
+ enable_critic_lstm=True,
34
+ activation_fn=nn.ReLU,
35
+ net_arch=dict(pi=[256, 256], vf=[256, 256]))
36
+ id: "1"
37
+ repo: "cboettig/rl4geco"
38
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
39
+ progress_bar: True
hyperpars/.ipynb_checkpoints/td3-gcmnorm-checkpoint.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "TD3"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0
13
+ id: "1"
14
+ repo: "cboettig/rl4geco"
15
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
16
+ progress_bar: True
hyperpars/.ipynb_checkpoints/tqc-gcmnorm-checkpoint.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "TQC"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0.3
13
+ use_sde: False
14
+ id: "1"
15
+ repo: "cboettig/rl4geco"
16
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
17
+ progress_bar: True
hyperpars/ppo-gcmnorm.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "PPO"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0
13
+ use_sde: False
14
+ id: "1"
15
+ repo: "cboettig/rl4geco"
16
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
17
+ progress_bar: True
hyperpars/rppo-gcmnorm.yml ADDED
@@ -0,0 +1,39 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: 'RecurrentPPO'
2
+ policy: "MultiInputLstmPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 15000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0.3
13
+ model_config:
14
+ 'verbose': 0
15
+ 'normalize_advantage': True
16
+ 'batch_size': 256,
17
+ 'n_steps': 1024,
18
+ 'gamma': 0.9999,
19
+ 'learning_rate': 0.0003,
20
+ 'ent_coef': 0.00429,
21
+ 'clip_range': 0.1,
22
+ 'n_epochs': 10,
23
+ 'gae_lambda': 0.9,
24
+ 'max_grad_norm': 0.5,
25
+ 'vf_coef': 0.19,
26
+ 'use_sde': False
27
+ 'sde_sample_freq': 8
28
+ 'tensorboard_log': "/home/rstudio/logs"
29
+ 'policy_kwargs': dict(log_std_init=0.0,
30
+ ortho_init=False,
31
+ lstm_hidden_size=256,
32
+ n_lstm_layers = 1,
33
+ enable_critic_lstm=True,
34
+ activation_fn=nn.ReLU,
35
+ net_arch=dict(pi=[256, 256], vf=[256, 256]))
36
+ id: "1"
37
+ repo: "cboettig/rl4geco"
38
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
39
+ progress_bar: True
hyperpars/td3-gcmnorm.yml ADDED
@@ -0,0 +1,16 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "TD3"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0
13
+ id: "1"
14
+ repo: "cboettig/rl4geco"
15
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
16
+ progress_bar: True
hyperpars/tqc-gcmnorm.yml ADDED
@@ -0,0 +1,17 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ algo: "TQC"
2
+ policy: "MultiInputPolicy"
3
+ env_id: "monthenvnorm"
4
+ n_envs: 12
5
+ tensorboard: "/home/rstudio/logs"
6
+ total_timesteps: 10000000
7
+ config:
8
+ "w_mort_scale" : 600
9
+ "growth_k": 0.70
10
+ 'random_start': True
11
+ "curriculum": False
12
+ 'var_penalty_const': 0.3
13
+ use_sde: False
14
+ id: "1"
15
+ repo: "cboettig/rl4geco"
16
+ save_path: "/home/rstudio/rl4greencrab/saved_agents"
17
+ progress_bar: True