NathanaelM commited on
Commit
22d383d
·
1 Parent(s): 6c5dc72

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: -138.87 +/- 82.57
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,14 +37,14 @@ 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': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
- 'gamma': 0.99
47
- 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'NathanaelM/ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -169.01 +/- 106.89
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': 0.00025
42
+ 'num_envs': 16
43
+ 'num_steps': 2048
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'NathanaelM/ppo-LunarLander-v2'
58
+ 'batch_size': 32768
59
+ 'minibatch_size': 8192}
60
  ```
61
 
logs/events.out.tfevents.1677253710.e6ac031e9814.10765.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:39713cd22ab6dc7fb5dc7fcc1bfb0db16d80e8ca3897f2d827fbb77fcbf82c4b
3
+ size 604435
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:3262cb9f8d71762568958150de91d2adbb7385c87e56d48030e8005230aa5d95
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:09a5d797a9f9a11b8cfa0f14ef044d8b938e0da31e2dfab92edea079437ef034
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": -138.86611686888256, "std_reward": 82.57163118544672, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-24T15:17:31.988740"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -169.00594731140365, "std_reward": 106.89072723647205, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-24T15:51:15.589573"}