mlewand commited on
Commit
9c70731
·
1 Parent(s): d2ab24a

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: -32.34 +/- 91.77
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': 1000000
41
  'learning_rate': 0.0001
42
- 'num_envs': 16
43
  'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
- 'gae_lambda': 0.8
48
  'num_minibatches': 64
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': 'mlewand/ppo-LunarLander-v2'
58
- 'batch_size': 16384
59
- 'minibatch_size': 256}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 80.67 +/- 117.50
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1250000
41
  'learning_rate': 0.0001
42
+ 'num_envs': 8
43
  'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
47
+ 'gae_lambda': 0.95
48
  'num_minibatches': 64
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'mlewand/ppo-LunarLander-v2'
58
+ 'batch_size': 8192
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1677422193.557f7251d789.20907.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:36acfd0cfd6f37a121bb78a4f3ce5ad9c832a2bc09c512554a0cfc94f8c357be
3
+ size 400768
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1553709ecd27456564c1d0ccd8a9de3e60b4e52026dfb56201c42f274936830e
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:24dc11ee67b3d1c1e8dad7dd67391100844cf8e1b999ba6b13a8520d30947d96
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": -32.34374847288065, "std_reward": 91.77280762920067, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T14:35:31.099101"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 80.66580930852513, "std_reward": 117.50288705090304, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-26T15:05:34.508820"}