daishan986 commited on
Commit
27e6736
·
verified ·
1 Parent(s): d07392b

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: 27.21 +/- 80.59
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,25 +37,25 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 3000000
41
- 'learning_rate': 0.0001
42
- 'num_envs': 8
43
- 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
- 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
- 'update_epochs': 10
50
  'norm_adv': True
51
  'clip_coef': 0.2
52
  'clip_vloss': True
53
- 'ent_coef': 0.05
54
  'vf_coef': 0.5
55
  'max_grad_norm': 0.5
56
- 'target_kl': 0.01
57
  'repo_id': 'daishan986/ppo-LunarLander-v2'
58
- 'batch_size': 8192
59
- 'minibatch_size': 2048}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 91.48 +/- 120.54
21
  name: mean_reward
22
  verified: false
23
  ---
 
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': 4
43
+ 'num_steps': 128
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.99
47
+ 'gae_lambda': 0.95
48
  'num_minibatches': 4
49
+ 'update_epochs': 4
50
  'norm_adv': True
51
  'clip_coef': 0.2
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': 'daishan986/ppo-LunarLander-v2'
58
+ 'batch_size': 512
59
+ 'minibatch_size': 128}
60
  ```
61
 
logs/events.out.tfevents.1760188656.bogon.18396.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cc0b1e844b4713daef56629d282616432f2990f2ae2e164ab2f3e1e2cc7e127f
3
+ size 1006259
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:6e8c920c125a5c1660b314b46ac0784196951f11c72abedd10ba4936d06c6d92
3
  size 43291
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e34a4f5e3ddebfeb2e89ec34a0fbee4c158fcff4d797345bc8804222b09dce22
3
  size 43291
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:f60f9b398b3957e736260cfa0b058f5a1252e8843b3f93c32b842195d005d966
3
- size 54765
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1489ae4eb853fe7d0e9de0b24584622ca0b4c61b67ddd14791d747c6bf06ce1e
3
+ size 98475
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": 27.21027515481064, "std_reward": 80.58560994471648, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-11T21:15:37.312949"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 91.47809151246027, "std_reward": 120.54422544776432, "n_evaluation_episodes": 10, "eval_datetime": "2025-10-11T21:19:57.288191"}