Sam017 commited on
Commit
de2e0f9
·
verified ·
1 Parent(s): 0a08a0a

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: -98.97 +/- 68.99
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': 1000000
41
- 'learning_rate': 0.00025
42
  'num_envs': 16
43
- 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
@@ -52,10 +52,10 @@ model-index:
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': 'Sam017/ppo-CartPole-v1'
58
- 'batch_size': 16384
59
- 'minibatch_size': 4096}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -1.44 +/- 66.01
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 1500000
41
+ 'learning_rate': 0.0003
42
  'num_envs': 16
43
+ 'num_steps': 2048
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
 
52
  'clip_vloss': True
53
  'ent_coef': 0.01
54
  'vf_coef': 0.5
55
+ 'max_grad_norm': 0.8
56
  'target_kl': None
57
  'repo_id': 'Sam017/ppo-CartPole-v1'
58
+ 'batch_size': 32768
59
+ 'minibatch_size': 8192}
60
  ```
61
 
logs/events.out.tfevents.1750885550.f8d56c68b18d.13669.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:97facdee42cc1da3ace3bc45e7309843d98431689afc9d709b12194d279effdf
3
+ size 1130539
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:ab62512b99c2fa4f992bbfaa1abc3df2cfd4904b1e1abb7b45d6d6a7ce45f5ac
3
  size 43026
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a383a49cb434fc06582c986916dbc77d9c5ae03bcd8f9f31242b4131840a4ad
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": -98.9690545146643, "std_reward": 68.99165614559064, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-25T21:04:38.219276"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -1.4411504252555574, "std_reward": 66.01400564182273, "n_evaluation_episodes": 10, "eval_datetime": "2025-06-25T21:17:36.375258"}