Malgesw commited on
Commit
f4f251f
·
verified ·
1 Parent(s): ca84e54

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: -171.72 +/- 124.21
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,10 +37,10 @@ model-index:
37
  'wandb_entity': None
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': 'ThomasSimonini/ppo-CartPole-v1'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -142.79 +/- 76.52
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 100000
41
+ 'learning_rate': 2.5e-05
42
+ 'num_envs': 8
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'ThomasSimonini/ppo-CartPole-v1'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1771279123.fedora.21612.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c593175398dfff51a2d2a993dd2babb7d042696a799c333d7831f315ebeda62e
3
+ size 149827
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6ee03726802455753871b25c2fa02cfb50b4be8c8cea8cb54cde62a65dc89383
3
  size 43419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7e15f6374dafb1e664e39f854d2636986200558bfee937ca7a4f14bde3cbe723
3
  size 43419
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": -171.71868842714278, "std_reward": 124.20606659206977, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-16T22:56:43.016382"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -142.79160469154564, "std_reward": 76.52177938826924, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-16T22:59:12.846508"}