carolinacon commited on
Commit
1965f19
·
verified ·
1 Parent(s): c439b7f

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: 73.47 +/- 77.72
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,8 +39,8 @@ model-index:
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': 0.999
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'carolinacon/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: -38.15 +/- 45.31
21
  name: mean_reward
22
  verified: false
23
  ---
 
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
+ 'num_envs': 8
43
+ 'num_steps': 256
44
  'anneal_lr': True
45
  'gae': True
46
  'gamma': 0.999
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'carolinacon/ppo-CartPole-v1'
58
+ 'batch_size': 2048
59
+ 'minibatch_size': 512}
60
  ```
61
 
logs/events.out.tfevents.1751466791.7c6da54d0a13.24357.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:246cd66c35ae1a78d1bb3c241d2859ed5a1cfbd0c3763da445093aecd026d81a
3
+ size 595595
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:95744401fcc8cfb0edb6a931f1cd983ecf9e05347bf0d7666e5d0187f6bf805d
3
  size 43419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d6e11af4cf48fa96d98b2954e09065446ae7ab43d664e864cc110730c1a1abb4
3
  size 43419
results.json CHANGED
@@ -1 +1 @@
1
- {"env_id": "LunarLander-v2", "mean_reward": 73.47403712022938, "std_reward": 77.72282262284084, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:26:22.544588"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -38.153958474420406, "std_reward": 45.30661379600637, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:37:42.808342"}