paranke commited on
Commit
f77f343
·
verified ·
1 Parent(s): 78e1484

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: -179.38 +/- 105.81
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -38,24 +38,24 @@ model-index:
38
  'capture_video': False
39
  'repo_id': 'paranke/ppo-LunarLander-from-scratch'
40
  'env_id': 'LunarLander-v2'
41
- 'total_timesteps': 50000
42
- 'learning_rate': 0.00025
43
  'num_envs': 4
44
- 'num_steps': 128
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
  'gae_lambda': 0.95
49
  'num_minibatches': 4
50
- 'update_epochs': 4
51
  'norm_adv': True
52
  'clip_coef': 0.2
53
  'clip_vloss': True
54
  'ent_coef': 0.01
55
- 'vf_coef': 0.5
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -132.08 +/- 84.44
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'repo_id': 'paranke/ppo-LunarLander-from-scratch'
40
  'env_id': 'LunarLander-v2'
41
+ 'total_timesteps': 65536
42
+ 'learning_rate': 2.5e-05
43
  'num_envs': 4
44
+ 'num_steps': 256
45
  'anneal_lr': True
46
  'gae': True
47
  'gamma': 0.99
48
  'gae_lambda': 0.95
49
  'num_minibatches': 4
50
+ 'update_epochs': 8
51
  'norm_adv': True
52
  'clip_coef': 0.2
53
  'clip_vloss': True
54
  'ent_coef': 0.01
55
+ 'vf_coef': 0.25
56
  'max_grad_norm': 0.5
57
  'target_kl': None
58
+ 'batch_size': 1024
59
+ 'minibatch_size': 256}
60
  ```
61
 
logs/events.out.tfevents.1732919709.fb28a0c4b3f0.6716.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c4f0da22dec00760be6164c3775cc2844e232dddc1d5cdcaf654f4199161818
3
+ size 117916
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:fd4596ab0794d2a541e1ee1543e4c0035dfad1fec7183bccf8aca2cae9fb97b0
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:701e87378bfb46aff8e1e530ed9ac3af969269146fd713f17e9da71c59f3d1dc
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": -179.3799833531339, "std_reward": 105.80765059666847, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-29T22:29:35.333301"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -132.07854776394947, "std_reward": 84.44415767772001, "n_evaluation_episodes": 10, "eval_datetime": "2024-11-29T22:36:06.806331"}