carolinacon commited on
Commit
1ff297a
·
verified ·
1 Parent(s): 1965f19

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: -38.15 +/- 45.31
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -40,7 +40,7 @@ model-index:
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
@@ -55,7 +55,7 @@ model-index:
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'carolinacon/ppo-CartPole-v1'
58
- 'batch_size': 2048
59
- 'minibatch_size': 512}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -98.81 +/- 52.05
21
  name: mean_reward
22
  verified: false
23
  ---
 
40
  'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
  'num_envs': 8
43
+ 'num_steps': 1024
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': 8192
59
+ 'minibatch_size': 2048}
60
  ```
61
 
logs/events.out.tfevents.1751467132.7c6da54d0a13.25805.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48c5c65428c3bf29541d1cdac18252518bd82a1f8bd1a2c1b808053eb8bd5be4
3
+ size 633364
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:d6e11af4cf48fa96d98b2954e09065446ae7ab43d664e864cc110730c1a1abb4
3
  size 43419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1192a893b8cf692eb50d801eec0cc1fc1183ee3e7ce56b306d31f02058ff7b46
3
  size 43419
results.json CHANGED
@@ -1 +1 @@
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"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -98.80954823765376, "std_reward": 52.046129027450306, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:42:25.885994"}