Push agent to the Hub
Browse files- README.md +5 -5
- logs/events.out.tfevents.1707493843.a74decb87bc7.6501.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
README.md
CHANGED
|
@@ -17,7 +17,7 @@ model-index:
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
-
value:
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
@@ -39,8 +39,8 @@ model-index:
|
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
'learning_rate': 0.0009
|
| 42 |
-
'num_envs':
|
| 43 |
-
'num_steps':
|
| 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': 'Katelie/lunarlander-cleanrl-ppo'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 0.79 +/- 79.35
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 50000
|
| 41 |
'learning_rate': 0.0009
|
| 42 |
+
'num_envs': 4
|
| 43 |
+
'num_steps': 32
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.999
|
|
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'Katelie/lunarlander-cleanrl-ppo'
|
| 58 |
+
'batch_size': 128
|
| 59 |
+
'minibatch_size': 32}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1707493843.a74decb87bc7.6501.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45d95677440c00395febc54bfe6a9f6c18e15bf231fad4fead7810600ce203ec
|
| 3 |
+
size 232038
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43026
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f15075304a175f6a28bb5ebd660e4daf95c9f837f7984e84dbb166178cbdafdc
|
| 3 |
size 43026
|
replay.mp4
CHANGED
|
Binary files a/replay.mp4 and b/replay.mp4 differ
|
|
|
results.json
CHANGED
|
@@ -1 +1 @@
|
|
| 1 |
-
{"env_id": "LunarLander-v2", "mean_reward":
|
|
|
|
| 1 |
+
{"env_id": "LunarLander-v2", "mean_reward": 0.7926786516925972, "std_reward": 79.34957627542444, "n_evaluation_episodes": 10, "eval_datetime": "2024-02-09T15:52:17.870225"}
|