slava-medvedev commited on
Commit
64d8e98
·
1 Parent(s): 2b5f1c5

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: -81.26 +/- 71.22
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,24 +38,24 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 100000
41
- 'learning_rate': 0.0001
42
  'num_envs': 4
43
- 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
- 'num_minibatches': 16
49
  'update_epochs': 8
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
- 'ent_coef': 0.05
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'slava-medvedev/unit8-ppo-LunarLander-v2'
58
- 'batch_size': 1024
59
- 'minibatch_size': 64}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -157.75 +/- 103.77
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 100000
41
+ 'learning_rate': 1e-05
42
  'num_envs': 4
43
+ 'num_steps': 512
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
  'gae_lambda': 0.95
48
+ 'num_minibatches': 4
49
  'update_epochs': 8
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': 'slava-medvedev/unit8-ppo-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1698342145.e81c8261624b.9421.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e87942c8176d21a117025d0afea54d94e51285c19daa0c454ad9f64f8419e267
3
+ size 154886
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:847376341ed258bba1e32f851a9721e98c0cfda74f09797be6cce92d3b57a5b2
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5608206a1fc5b12649b14490b2c8ca35b8077c0007dafed403336b4f8d0be163
3
  size 43026
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": -81.25575369404757, "std_reward": 71.22034112908497, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:41:41.259702"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -157.7511752333309, "std_reward": 103.7688030724314, "n_evaluation_episodes": 10, "eval_datetime": "2023-10-26T17:43:40.857139"}