miki030 commited on
Commit
7ebd099
·
1 Parent(s): 8625047

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: -53.53 +/- 26.50
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,9 +38,9 @@ model-index:
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 5000000
41
- 'learning_rate': 2.5e-05
42
  'num_envs': 128
43
- 'num_steps': 64
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.995
@@ -50,12 +50,12 @@ model-index:
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
- 'ent_coef': 0.001
54
  'vf_coef': 0.5
55
- 'max_grad_norm': 0.4
56
  'target_kl': None
57
  'repo_id': 'miki030/lunar2'
58
- 'batch_size': 8192
59
- 'minibatch_size': 2048}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 142.56 +/- 50.13
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 5000000
41
+ 'learning_rate': 0.0025
42
  'num_envs': 128
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.995
 
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': 'miki030/lunar2'
58
+ 'batch_size': 32768
59
+ 'minibatch_size': 8192}
60
  ```
61
 
logs/events.out.tfevents.1693220346.d39058c94989.54246.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f40274b78473f01f5d7d0808d66b96d249f41f66f91e854d359f1507f95c7043
3
+ size 944042
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:a2c93c33936430fc5fbd791282294a9dc866927ddfee3a8b6df7c843c744db0f
3
- size 12693275
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc9306f39a4b538e46321ecbff9f13e1a55d1924cd879d3d9afa62f9bd86f0fa
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": -53.52862799039025, "std_reward": 26.49729914744722, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T10:42:10.096320"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 142.5598002879668, "std_reward": 50.12704857927832, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T12:42:03.914804"}