Fetanos commited on
Commit
3a049e9
1 Parent(s): 0f9b041

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: -147.06 +/- 78.75
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': 50000
41
- 'learning_rate': 0.00025
42
  'num_envs': 4
43
- 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Fetanos/ppo-LunarLander-v2-2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -31.85 +/- 52.03
21
  name: mean_reward
22
  verified: false
23
  ---
 
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 50000
41
+ 'learning_rate': 0.01
42
  'num_envs': 4
43
+ 'num_steps': 300
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'Fetanos/ppo-LunarLander-v2-2'
58
+ 'batch_size': 1200
59
+ 'minibatch_size': 300}
60
  ```
61
 
logs/events.out.tfevents.1716227772.9fcd669d44f2.5316.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1a591ff4313ed2ca96238ca5368c62e2c0dc1f41fd0175214f5924fe8160bca6
3
+ size 63588
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:b51141f29a5fd60d9f7a96a70a1e185897fcb1c4838b12131a7276001db13c08
3
  size 42898
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:32065964ebb711e127ab3bc175302ecf649f5aa72f92f6645d9f8b4d8efb027c
3
  size 42898
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": -147.0561131121364, "std_reward": 78.75388917342657, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-20T17:53:34.176140"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -31.85265324400814, "std_reward": 52.034063777967596, "n_evaluation_episodes": 10, "eval_datetime": "2024-05-20T17:56:51.968966"}