carolinacon commited on
Commit
8be20aa
·
verified ·
1 Parent(s): 1ff297a

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: -98.81 +/- 52.05
21
  name: mean_reward
22
  verified: false
23
  ---
@@ -39,7 +39,7 @@ model-index:
39
  'env_id': 'LunarLander-v2'
40
  'total_timesteps': 500000
41
  'learning_rate': 0.00025
42
- 'num_envs': 8
43
  'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
@@ -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': 8192
59
- 'minibatch_size': 2048}
60
  ```
61
 
 
17
  type: LunarLander-v2
18
  metrics:
19
  - type: mean_reward
20
+ value: -135.14 +/- 57.40
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': 16
43
  'num_steps': 1024
44
  'anneal_lr': True
45
  'gae': True
 
55
  'max_grad_norm': 0.5
56
  'target_kl': None
57
  'repo_id': 'carolinacon/ppo-CartPole-v1'
58
+ 'batch_size': 16384
59
+ 'minibatch_size': 4096}
60
  ```
61
 
logs/events.out.tfevents.1751467412.7c6da54d0a13.26970.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb7a0b43d039645122640b3d9f0dcf0ca26b2a0c55620f216b72f3f1c1484f23
3
+ size 611320
model.pt CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:1192a893b8cf692eb50d801eec0cc1fc1183ee3e7ce56b306d31f02058ff7b46
3
  size 43419
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c8b6ee6d35aa725f732392261cb37b102fdbe0884c52ba4fccbfd6710bc51ec4
3
  size 43419
results.json CHANGED
@@ -1 +1 @@
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"}
 
1
+ {"env_id": "LunarLander-v2", "mean_reward": -135.13644272858255, "std_reward": 57.39682432371917, "n_evaluation_episodes": 10, "eval_datetime": "2025-07-02T14:46:02.514514"}