Push agent to the Hub
Browse files- README.md +4 -4
- logs/events.out.tfevents.1718027340.887b5cfc0142.20608.0 +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 |
---
|
|
@@ -40,7 +40,7 @@ model-index:
|
|
| 40 |
'total_timesteps': 50000
|
| 41 |
'learning_rate': 0.003
|
| 42 |
'num_envs': 16
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.98
|
|
@@ -55,7 +55,7 @@ model-index:
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -156.22 +/- 69.95
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 40 |
'total_timesteps': 50000
|
| 41 |
'learning_rate': 0.003
|
| 42 |
'num_envs': 16
|
| 43 |
+
'num_steps': 1024
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
'gamma': 0.98
|
|
|
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
'target_kl': None
|
| 57 |
'repo_id': 'arhamk/ppo-LunarLander-v2-2'
|
| 58 |
+
'batch_size': 16384
|
| 59 |
+
'minibatch_size': 4096}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1718027340.887b5cfc0142.20608.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9560b7f0b6df603e3dc7bdc06f8623384e4f464c0fbd8dee10a4e092d0c49e7e
|
| 3 |
+
size 58755
|
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 sha256:0c338d11f5c4c434eee52af7c40c09ab05fb6c34e9b87e8cdf9b75ea5c6c5a35
|
| 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": -156.22237483923155, "std_reward": 69.95293744111738, "n_evaluation_episodes": 10, "eval_datetime": "2024-06-10T13:49:20.602416"}
|