jannikskytt commited on
Commit
b49e272
1 Parent(s): 771714a

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: -7.89 +/- 119.28
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,9 +37,9 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 2500000
41
  'learning_rate': 0.00025
42
- 'num_envs': 4
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jannikskytt/ppo-implemented-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -105.68 +/- 49.60
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 3500000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 16
43
  'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'jannikskytt/ppo-implemented-LunarLander-v2'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1676640160.TEK-CB-JASP-01.5560.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:578b049e223b93f5c7e19add506fa6b81f7d49d33bf6f9716fa2da27ed876169
3
+ size 1647095
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0375c90ef0c3f3229dbbebb0d54001af5d883ee2393372750d5b35ae96221f99
3
  size 42469
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e9322800bffcb2e21526d2411568e8a05f77c2a22ac426fc29a973649cad4387
3
  size 42469
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": -7.8853186069335255, "std_reward": 119.27598205433243, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T13:36:19.405755"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -105.68109376382995, "std_reward": 49.59528008052757, "n_evaluation_episodes": 10, "eval_datetime": "2023-02-17T15:59:09.847115"}