Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1693212135.d39058c94989.20377.0 +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 |
---
|
|
@@ -39,7 +39,7 @@ model-index:
|
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 500000
|
| 41 |
'learning_rate': 2.5e-05
|
| 42 |
-
'num_envs':
|
| 43 |
'num_steps': 64
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
|
@@ -55,7 +55,7 @@ model-index:
|
|
| 55 |
'max_grad_norm': 0.2
|
| 56 |
'target_kl': 0.015
|
| 57 |
'repo_id': 'miki030/lunar2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -129.04 +/- 112.39
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 500000
|
| 41 |
'learning_rate': 2.5e-05
|
| 42 |
+
'num_envs': 128
|
| 43 |
'num_steps': 64
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
|
|
|
| 55 |
'max_grad_norm': 0.2
|
| 56 |
'target_kl': 0.015
|
| 57 |
'repo_id': 'miki030/lunar2'
|
| 58 |
+
'batch_size': 8192
|
| 59 |
+
'minibatch_size': 2048}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1693212135.d39058c94989.20377.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf9fb0c830c4abc953e2f9696e609abd2dd2c49cedc42124ac6c644be5e1e27c
|
| 3 |
+
size 382694
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 8494437
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd2543fcfcf02d6fc8a4d545c00a48e93704a2929f9a41d16b5eb5371483f930
|
| 3 |
size 8494437
|
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": -129.04191177884766, "std_reward": 112.3893775242826, "n_evaluation_episodes": 10, "eval_datetime": "2023-08-28T08:44:18.617629"}
|