DevozZ commited on
Commit
b9e6407
·
1 Parent(s): eebd88c

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: -170.98 +/- 86.67
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,9 +37,9 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 50000
41
- 'learning_rate': 0.00025
42
- 'num_envs': 10
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'DevozZ/LunarLander-v2'
58
- 'batch_size': 1280
59
- 'minibatch_size': 320}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -58.93 +/- 81.11
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 500000
41
+ 'learning_rate': 0.001
42
+ 'num_envs': 16
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'DevozZ/LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1684684400.20a5be0b38b2.18596.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9c4f32dd0499ca5a5e3899d2c1cf396b984fedec1424ce7fea24b68cce9f48e0
3
+ size 126332
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:61721065c8cab383ca422180761d29a0e04c9b6df5a13c8927f98f020c04b4bc
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d5d5969a9af92ae02f3bcc95844be3dbf24e2b9509a48263d51f0078f4d780f
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": -170.97515484926112, "std_reward": 86.67399723162059, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-21T15:49:24.091976"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -58.93486150441438, "std_reward": 81.11372137769334, "n_evaluation_episodes": 10, "eval_datetime": "2023-05-21T16:06:07.591814"}