naeisher commited on
Commit
ea68d96
1 Parent(s): d76e3c2

Push agent to the Hub

Browse files
README.md CHANGED
@@ -17,7 +17,7 @@ model-index:
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
- value: -98.52 +/- 79.04
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -29,7 +29,7 @@ model-index:
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'ppo'
32
- 'seed': 123
33
  'torch_deterministic': True
34
  'cuda': True
35
  'track': False
@@ -37,7 +37,7 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
  'learning_rate': 0.0003
42
  'num_envs': 4
43
  'num_steps': 2048
@@ -48,10 +48,10 @@ model-index:
48
  'num_minibatches': 32
49
  'update_epochs': 10
50
  'norm_adv': True
51
- 'clip_coef': 0.2
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
- 'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'naeisher/LunarLander-v2'
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -90.85 +/- 99.38
21
  name: mean_reward
22
  verified: false
23
  ---
 
29
  # Hyperparameters
30
  ```python
31
  {'exp_name': 'ppo'
32
+ 'seed': 1
33
  'torch_deterministic': True
34
  'cuda': True
35
  'track': False
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 100000
41
  'learning_rate': 0.0003
42
  'num_envs': 4
43
  'num_steps': 2048
 
48
  'num_minibatches': 32
49
  'update_epochs': 10
50
  'norm_adv': True
51
+ 'clip_coef': 0.1
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
+ 'vf_coef': 0.25
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'naeisher/LunarLander-v2'
logs/events.out.tfevents.1679877145.2a0c170730d9.66096.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2a8a4f1c22650fc0336a56df5c2a854f7c88a5d58b6326b967198c83b47468af
3
+ size 112829
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:24d7a8f003310248ed9b402b7ff9aaaef0940a4fbd38c23aa5af8deca2484d04
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e33d8bfe623364086eba7c975d8f523c46bfb881245f6696ebb7a647f397e1a
3
  size 42597
replay.mp4 CHANGED
Binary files a/replay.mp4 and b/replay.mp4 differ
 
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": -98.51745075823956, "std_reward": 79.0364477723855, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:12:47.474156"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -90.8481268785036, "std_reward": 99.37951860354941, "n_evaluation_episodes": 10, "eval_datetime": "2023-03-27T00:34:10.376939"}