chauvanphuoc commited on
Commit
9956342
·
verified ·
1 Parent(s): 52efd2e

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: 10.75 +/- 122.75
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -37,14 +37,14 @@ model-index:
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
- 'total_timesteps': 500000
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
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'chauvanphuoc/ppo-LunarLander-v2'
58
- 'batch_size': 512
59
- 'minibatch_size': 128}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: 124.39 +/- 17.82
21
  name: mean_reward
22
  verified: false
23
  ---
 
37
  'wandb_entity': None
38
  'capture_video': False
39
  'env_id': 'LunarLander-v2'
40
+ 'total_timesteps': 3000000
41
  'learning_rate': 0.00025
42
  'num_envs': 4
43
+ 'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
46
+ 'gamma': 0.999
47
+ 'gae_lambda': 0.98
48
  'num_minibatches': 4
49
  'update_epochs': 4
50
  'norm_adv': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'chauvanphuoc/ppo-LunarLander-v2'
58
+ 'batch_size': 4096
59
+ 'minibatch_size': 1024}
60
  ```
61
 
logs/events.out.tfevents.1764945913.1box.814238.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:564c901eeb7ad609d5c29adc374e8bee59f02763afee4682a8564bebdf47f0bf
3
+ size 1276536
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:0f19e67ef1e54b30d33431701994ab9c64ff58acef6b32f9a6002f741a6e31c6
3
  size 42597
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6df37f2d488b46b008aed4454af8fd10dc7917fb550502e89c0edf2462322e15
3
  size 42597
replay.mp4 CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:13cf25ada9af970ecc933be8e6473edf5478be65116c1c691b4f608835ec2cd2
3
- size 133610
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:be89fcfc7a70f1b49869fdb87d87af1d757517604700eada2709949331f71d26
3
+ size 157978
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": 10.75021467649027, "std_reward": 122.74759155532217, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-05T14:27:30.173811"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": 124.38766671217056, "std_reward": 17.81730000074012, "n_evaluation_episodes": 10, "eval_datetime": "2025-12-05T15:07:11.120499"}