Push agent to the Hub
Browse files- .gitattributes +1 -0
- README.md +9 -9
- logs/events.out.tfevents.1771117928.86cf83882442.13633.0 +3 -0
- model.pt +1 -1
- replay.mp4 +0 -0
- results.json +1 -1
.gitattributes
CHANGED
|
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
replay.mp4 filter=lfs diff=lfs merge=lfs -text
|
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 |
---
|
|
@@ -38,24 +38,24 @@ model-index:
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 1000000
|
| 41 |
-
'learning_rate': 0.
|
| 42 |
'num_envs': 16
|
| 43 |
-
'num_steps':
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
-
'gamma': 0.
|
| 47 |
-
'gae_lambda': 0.
|
| 48 |
'num_minibatches': 4
|
| 49 |
-
'update_epochs':
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
| 53 |
'ent_coef': 0.01
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
-
'target_kl':
|
| 57 |
'repo_id': 'Chiz/ppo-LunarLander-v2'
|
| 58 |
-
'batch_size':
|
| 59 |
-
'minibatch_size':
|
| 60 |
```
|
| 61 |
|
|
|
|
| 17 |
type: LunarLander-v2
|
| 18 |
metrics:
|
| 19 |
- type: mean_reward
|
| 20 |
+
value: -30.14 +/- 25.63
|
| 21 |
name: mean_reward
|
| 22 |
verified: false
|
| 23 |
---
|
|
|
|
| 38 |
'capture_video': False
|
| 39 |
'env_id': 'LunarLander-v2'
|
| 40 |
'total_timesteps': 1000000
|
| 41 |
+
'learning_rate': 0.00025
|
| 42 |
'num_envs': 16
|
| 43 |
+
'num_steps': 1024
|
| 44 |
'anneal_lr': True
|
| 45 |
'gae': True
|
| 46 |
+
'gamma': 0.99
|
| 47 |
+
'gae_lambda': 0.95
|
| 48 |
'num_minibatches': 4
|
| 49 |
+
'update_epochs': 10
|
| 50 |
'norm_adv': True
|
| 51 |
'clip_coef': 0.2
|
| 52 |
'clip_vloss': True
|
| 53 |
'ent_coef': 0.01
|
| 54 |
'vf_coef': 0.5
|
| 55 |
'max_grad_norm': 0.5
|
| 56 |
+
'target_kl': None
|
| 57 |
'repo_id': 'Chiz/ppo-LunarLander-v2'
|
| 58 |
+
'batch_size': 16384
|
| 59 |
+
'minibatch_size': 4096}
|
| 60 |
```
|
| 61 |
|
logs/events.out.tfevents.1771117928.86cf83882442.13633.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b810db192a7fccb48be3c2ffc24bcebc1dd76f51fc6ea5ef59ab5bf8e3600ad0
|
| 3 |
+
size 397386
|
model.pt
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
size 43419
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:718d6a8eadeb13f5c65c3539ff05e15e3c8819319ba8364f38773dd861db902a
|
| 3 |
size 43419
|
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": -30.13895288952446, "std_reward": 25.633584143083027, "n_evaluation_episodes": 10, "eval_datetime": "2026-02-15T01:31:49.752840"}
|