Push agent to the Hub
Browse files- README.md +6 -6
- logs/events.out.tfevents.1680455516.DESKTOP-8KVI3JI.20857.0 +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 |
---
|
|
@@ -37,9 +37,9 @@ model-index:
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
-
'total_timesteps':
|
| 41 |
-
'learning_rate': 0.
|
| 42 |
-
'num_envs':
|
| 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': 'mark-e/ppo_custom-LunarLander-v2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: 135.53 +/- 15.73
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 37 |
'wandb_entity': None
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
+
'total_timesteps': 5000000
|
| 41 |
+
'learning_rate': 0.0003
|
| 42 |
+
'num_envs': 64
|
| 43 |
'num_steps': 1024
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
|
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'mark-e/ppo_custom-LunarLander-v2'
|
| 58 |
+
'batch_size': 65536
|
| 59 |
+
'minibatch_size': 1024}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1680455516.DESKTOP-8KVI3JI.20857.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a937815b3d3368c9bb238933bffb57f6c7a88cceb3db8e0bd360d13201890253
|
| 3 |
+
size 1123187
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 42817
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4ecfcb2f8d9fb05a6fbebe55b59b7da1e2ae67cc38335df8cfcc03e84f857c70
|
| 3 |
size 42817
|
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": 135.53375775390086, "std_reward": 15.728853582724263, "n_evaluation_episodes": 10, "eval_datetime": "2023-04-02T19:07:27.774821"}
|